© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 157687
    Prev
    Next
    INDEX
    Explanations

    attribute values, largely contingent, attached roofs, storm the

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

    programming function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     them
    0.50
    ą
    0.50
    fromi
    0.47
     said
    0.46
    ى
    0.46
    _
    0.46
    A
    0.43
    展
    0.43
     san
    0.43
     tea
    0.42
    POSITIVE LOGITS
    ठभे
    0.52
    ꯦ
    0.49
    =?,
    0.49
     optimist
    0.45
    ↼
    0.44
     प्रभ
    0.44
    ኸ
    0.44
     aclarar
    0.42
    𒁕
    0.42
    োপাধ
    0.42
    Activations Density 0.001%

    No Known Activations