© 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. 3054
    Prev
    Next
    INDEX
    Explanations

    numbers and time units

    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
     what
    -1.27
     Surprisingly
    -1.20
    Surprisingly
    -1.19
     one
    -1.14
    SBATCH
    -1.09
     Some
    -1.05
    Before
    -1.05
    ＂
    -1.03
     any
    -1.03
    There
    -1.02
    POSITIVE LOGITS
    捱
    1.08
    厲
    1.04
     AMAZING
    1.04
    了一遍
    1.04
     ludicrous
    1.03
     angeboten
    1.03
    nag
    1.00
     coloca
    0.99
     eas
    0.98
    ⩥
    0.97
    Activations Density 0.428%

    No Known Activations