© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63835
    Prev
    Next
    INDEX
    Explanations

    is survived by

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on the present‐tense copula “is” (often followed by a past participle or adjective), flagging descriptive or biographical “X is…” statements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     which
    -0.93
    jected
    -0.88
    𝔪
    -0.83
    炊き
    -0.82
    當時
    -0.81
     menak
    -0.81
     всегда
    -0.81
    擔心
    -0.80
    してみた
    -0.80
    hibition
    -0.78
    POSITIVE LOGITS
     survived
    3.41
    Survi
    1.70
     survives
    1.63
    survi
    1.53
     survive
    1.52
     Survi
    1.46
     survi
    1.45
     preceded
    1.43
     remembered
    1.41
     sobrevi
    1.38
    Activations Density 0.008%

    No Known Activations