© 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. 128300
    Prev
    Next
    INDEX
    Explanations

    names, initials, 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_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
     stora
    -1.41
    }.
    -1.40
     дошко
    -1.38
    }
    -1.34
     process
    -1.29
     eran
    -1.28
     Bezir
    -1.27
    ();
    -1.26
    勧め
    -1.26
    ();
    -1.24
    POSITIVE LOGITS
     udang
    1.37
     intentó
    1.36
    uyasha
    1.36
     ofreció
    1.36
    Nasc
    1.36
    Público
    1.34
     connexions
    1.32
    Примеча
    1.30
     सत्यापित
    1.30
     trató
    1.30
    Activations Density 0.010%

    No Known Activations