© 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. 67476
    Prev
    Next
    INDEX
    Explanations

    insult and affront

    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
    ꯳
    -2.28
     were
    -2.27
    sonaro
    -2.14
    Efter
    -2.05
    %">
    -2.02
     my
    -1.98
    ﾋ
    -1.98
    ᵴ
    -1.93
    ﾊ
    -1.93
    viève
    -1.93
    POSITIVE LOGITS
    ↵↵
    3.23
    ↵
    2.97
    .
    2.41
    \
    2.30
    }
    2.27
    also
    2.22
    ti
    2.19
    "
    2.17
     también
    2.14
    “
    2.05
    Activations Density 0.004%

    No Known Activations