© 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. 128756
    Prev
    Next
    INDEX
    Explanations

    note that

    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
    )
    -2.81
     a
    -2.36
    ;
    -2.11
    :
    -1.97
    }
    -1.87
    ]
    -1.82
     $\
    -1.77
    >
    -1.62
    us
    -1.58
    .”
    -1.56
    POSITIVE LOGITS
    閙
    2.00
     there
    1.81
    することも
    1.76
    慙
    1.73
    ︕
    1.70
     ataupun
    1.70
     ţ
    1.70
    cayaan
    1.69
    ￨
    1.67
    ⃤
    1.67
    Activations Density 0.010%

    No Known Activations