© 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. 72148
    Prev
    Next
    INDEX
    Explanations

    throw followed by varied actions

    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
    which
    -3.64
    j
    -3.00
     tries
    -2.73
    H
    -2.66
    IS
    -2.66
    G
    -2.63
    n
    -2.61
    from
    -2.55
    From
    -2.52
    This
    -2.50
    POSITIVE LOGITS
    ᥬ
    2.98
     criada
    2.91
    歃
    2.75
     gelb
    2.61
    ⬈
    2.59
    dpy
    2.33
     beginnen
    2.33
    滹
    2.31
    xnn
    2.30
     rechte
    2.27
    Activations Density 0.008%

    No Known Activations