© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 63189
    Prev
    Next
    INDEX
    Explanations

    top or topical prefix

    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
    ower
    -1.11
     perfekte
    -0.88
     devront
    -0.84
    pkt
    -0.84
     gelatina
    -0.83
     epoca
    -0.78
    켜
    -0.78
    夸张
    -0.77
     collapsing
    -0.77
    hq
    -0.76
    POSITIVE LOGITS
    most
    1.70
    notch
    1.45
    ically
    1.33
    flight
    1.16
     notch
    1.09
     tier
    1.08
     pf
    1.06
    coat
    1.02
     TOP
    0.99
    排行榜
    0.98
    Activations Density 0.040%

    No Known Activations