© 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. 59195
    Prev
    Next
    INDEX
    Explanations

    fam and family members

    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
    ↵
    -3.58
    蟜
    -3.19
    ︲
    -2.92
    趼
    -2.91
    想了想
    -2.81
    ”.
    -2.66
    </sub>
    -2.66
     bús
    -2.61
     were
    -2.58
    </h3>
    -2.55
    POSITIVE LOGITS
    遢
    2.66
    We
    2.52
    )
    2.45
     Fam
    2.36
     There
    2.36
    O
    2.27
    When
    2.25
    تیجه
    2.23
    是
    2.22
    \
    2.20
    Activations Density 0.005%

    No Known Activations