© 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. 22-GEMMASCOPE-RES-131K
    4. 33984
    Prev
    Next
    INDEX
    Explanations

    press release dateline identifiers

    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
     are
    -1.37
    </h1>
    -1.29
    providedIn
    -1.26
     않는
    -1.23
    </h2>
    -1.20
    ]);
    -1.16
    }{*}{
    -1.12
    ])):
    -1.12
    ]));
    -1.11
    ())->
    -1.10
    POSITIVE LOGITS
    راً
    1.04
    ifes
    1.04
     réve
    1.03
     Lumb
    1.02
     bestanden
    1.02
     rencont
    1.02
    からない
    1.01
     VOID
    1.00
     rembourse
    1.00
     réjou
    1.00
    Activations Density 0.002%

    No Known Activations