© 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. 91638
    Prev
    Next
    INDEX
    Explanations

    "Having" followed by past states

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ՛
    -1.37
     and
    -1.25
     póster
    -1.24
    ⁽
    -1.20
    éndole
    -1.18
    戗
    -1.16
     has
    -1.16
    ੦
    -1.13
    😓
    -1.13
    ยัง
    -1.12
    POSITIVE LOGITS
     been
    2.70
     spent
    2.02
     lived
    1.77
     said
    1.73
     previously
    1.73
     recently
    1.63
     heard
    1.46
     watched
    1.44
     read
    1.41
     seen
    1.39
    Activations Density 0.020%

    No Known Activations