© 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. 22-GEMMASCOPE-RES-131K
    7. 72435
    Prev
    Next
    INDEX
    Explanations

    as if, if, simulate

    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
     가능
    -1.00
    첵
    -0.98
     influen
    -0.93
     هن
    -0.88
    Ident
    -0.87
     پیک
    -0.86
     لهذه
    -0.85
    很赞
    -0.85
     ווי
    -0.85
    coconut
    -0.84
    POSITIVE LOGITS
    ();*/
    0.93
     a
    0.88
     ++
    0.86
     having
    0.85
     as
    0.84
    '}}
    0.84
     pelas
    0.83
     while
    0.82
    force
    0.81
    ➡
    0.81
    Activations Density 0.039%

    No Known Activations