© 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. 99410
    Prev
    Next
    INDEX
    Explanations

    lists of items or actions

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

    conversation and confidentiality

    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
    d
    0.54
    and
    0.50
    x
    0.48
    z
    0.47
    1
    0.46
    j
    0.43
    b
    0.43
     dalších
    0.42
     hakk
    0.42
     jangka
    0.42
    POSITIVE LOGITS
     మాట్లాడు
    0.48
     консо
    0.48
     Quarry
    0.47
    硖
    0.47
     inconsistent
    0.46
     Conversation
    0.45
    桥
    0.45
     Conservatory
    0.44
    磴
    0.44
     Structural
    0.44
    Activations Density 0.001%

    No Known Activations