© 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. 22-GEMMASCOPE-RES-131K
    7. 34217
    Prev
    Next
    INDEX
    Explanations

    media formats

    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_22/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
     —
    -1.56
    q
    -1.55
    RE
    -1.52
    b
    -1.50
    j
    -1.49
     -
    -1.49
    </b>
    -1.48
    U
    -1.47
    O
    -1.47
    f
    -1.47
    POSITIVE LOGITS
    𐐪
    1.49
     coute
    1.46
    𓆜
    1.45
    ꪗ
    1.43
    nemies
    1.43
    𓏸
    1.41
    Только
    1.41
    媖
    1.39
    亊
    1.39
     esqueleto
    1.39
    Activations Density 0.022%

    No Known Activations