© 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. 10-GEMMASCOPE-RES-131K
    7. 128543
    Prev
    Next
    INDEX
    Explanations

    copyright notices

    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_10/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
     detenido
    -1.53
    ᚔ
    -1.49
     decidido
    -1.45
    嵎
    -1.45
     enamorado
    -1.44
     trasladado
    -1.44
     interesado
    -1.41
    岽
    -1.40
     comprometido
    -1.40
     dél
    -1.39
    POSITIVE LOGITS
    </i>
    2.06
     have
    1.96
     how
    1.73
    >-->
    1.66
     he
    1.63
    </strong>
    1.52
     each
    1.45
     of
    1.43
    на
    1.42
     some
    1.37
    Activations Density 0.046%

    No Known Activations