© 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. 203295
    Prev
    Next
    INDEX
    Explanations

    WAR and SCA

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

    Planning and harm

    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
     fiable
    0.50
     ľ
    0.50
     பல்கலை
    0.48
    abilidad
    0.47
    𝚗
    0.47
    ismo
    0.47
    ට්
    0.47
     sami
    0.46
     aparato
    0.46
     если
    0.46
    POSITIVE LOGITS
     sections
    0.43
    WARDS
    0.43
    については
    0.40
     Dorchester
    0.39
     Michaelmas
    0.39
     additions
    0.38
     Revisited
    0.38
    ＝
    0.38
    簟
    0.38
    PRESS
    0.38
    Activations Density 0.003%

    No Known Activations