© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 104683
    Prev
    Next
    INDEX
    Explanations

    comparative quantity or ranking

    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_22/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
    がありますが
    -1.69
    などが
    -1.59
    を
    -1.41
    は
    -1.37
    が
    -1.36
     of
    -1.34
    と
    -1.34
    と思っていた
    -1.33
    などは
    -1.26
    ebly
    -1.25
    POSITIVE LOGITS
     or
    1.83
    ところに
    1.41
    catchError
    1.17
    為に
    1.13
     available
    1.13
    ساء
    1.11
    طه
    1.09
     случайно
    1.09
     dava
    1.08
     manchas
    1.07
    Activations Density 0.072%

    No Known Activations