© 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. 64197
    Prev
    Next
    INDEX
    Explanations

    enum values

    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
     and
    -1.34
     the
    -1.24
     Thirty
    -1.21
     Forty
    -1.13
    💗
    -1.11
    💙
    -1.09
     forty
    -1.09
     fourteen
    -1.08
    หรือ
    -1.05
     eighteen
    -1.05
    POSITIVE LOGITS
    _
    1.08
    else
    1.08
     '*':
    1.06
    ?.
    1.02
    ations
    1.02
    などを
    1.01
     overarching
    0.98
    小孩子
    0.98
    人に
    0.98
    ance
    0.98
    Activations Density 0.055%

    No Known Activations