© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91607
    Prev
    Next
    INDEX
    Explanations

    past states and actions

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

    The neuron is specialized to detect four‐digit numeric tokens, i.e. years or date numbers.

    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
    ksamkeit
    -1.20
     ahora
    -1.13
     nuevos
    -1.13
     sekarang
    -1.09
    ベーター
    -1.06
    timme
    -1.05
    ("")]
    -1.04
     majú
    -1.03
     június
    -1.02
    ='',
    -1.02
    POSITIVE LOGITS
     later
    1.73
     eventually
    1.51
     finally
    1.51
     first
    1.48
     also
    1.46
     used
    1.45
     one
    1.38
     subsequently
    1.33
     initially
    1.30
     considered
    1.19
    Activations Density 0.127%

    No Known Activations