© 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. 10-GEMMASCOPE-RES-131K
    7. 67120
    Prev
    Next
    INDEX
    Explanations

    timestamps and dates

    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_10/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
    を変える
    -1.47
     feil
    -1.40
    amblea
    -1.39
     klokken
    -1.38
     budapest
    -1.38
     conduire
    -1.37
     подготовка
    -1.36
    誣
    -1.36
     hii
    -1.35
     Jugos
    -1.34
    POSITIVE LOGITS
    Since
    1.65
     —
    1.63
    Any
    1.55
    近年
    1.51
    Until
    1.49
    Recently
    1.48
    </h1>
    1.45
    Please
    1.45
    Through
    1.45
    Currently
    1.44
    Activations Density 0.008%

    No Known Activations