© 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. 34-GEMMASCOPE-RES-131K
    7. 93104
    Prev
    Next
    INDEX
    Explanations

    cryptography or code execution

    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_34/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
    Willy
    -0.87
     our
    -0.85
    辎
    -0.82
    pięk
    -0.82
    katalog
    -0.81
    Aur
    -0.81
    󠁳
    -0.81
    estudiante
    -0.78
    automation
    -0.77
    untut
    -0.77
    POSITIVE LOGITS
     Dinge
    0.83
    um
    0.82
    8
    0.80
    その
    0.79
    [...]
    0.79
    whether
    0.77
    Success
    0.76
     STARTED
    0.75
     fn
    0.74
    lash
    0.73
    Activations Density 0.043%

    No Known Activations