© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102910
    Prev
    Next
    INDEX
    Explanations

    causes and effects

    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
    </b>
    -1.60
    })}
    -1.55
    }$
    -1.55
    !),
    -1.41
    事は
    -1.34
     détaillé
    -1.33
    It
    -1.31
     последний
    -1.30
    )=(
    -1.29
     conocida
    -1.29
    POSITIVE LOGITS
     from
    1.56
     with
    1.52
    s
    1.26
    ㅌ
    1.23
    árol
    1.23
     Our
    1.19
     preferências
    1.17
     töd
    1.16
    ɵɵelement
    1.14
     afectan
    1.14
    Activations Density 0.025%

    No Known Activations