© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 47382
    Prev
    Next
    INDEX
    Explanations

    actions leading to destruction

    np_acts-logits-general · gemini-2.5-flash-lite

    outlining tasks, agreements, or schemas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Workflow
    0.51
     Prospect
    0.50
    Prospect
    0.50
    "
    0.45
    O
    0.45
    Strategy
    0.44
    <unused61>
    0.43
    Peaks
    0.43
    Outgoing
    0.42
     Zeitraum
    0.42
    POSITIVE LOGITS
    ()):
    0.41
     illusions
    0.40
     cutters
    0.39
     confronts
    0.39
     fortified
    0.39
    女
    0.39
    стры
    0.38
     confronted
    0.38
     때문이다
    0.38
     armies
    0.38
    Activations Density 0.000%

    No Known Activations