© 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. 95515
    Prev
    Next
    INDEX
    Explanations

    attack or event

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

    eradicating, commit more, harmed the world

    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
    5
    0.54
    6
    0.54
    1
    0.52
    4
    0.50
     be
    0.49
    ↵↵
    0.46
     Colo
    0.45
    Am
    0.44
    Bone
    0.42
    7
    0.42
    POSITIVE LOGITS
     sämt
    0.56
     onslaught
    0.49
    অর্থাৎ
    0.47
    сій
    0.47
     завдання
    0.46
    ştur
    0.46
    бий
    0.46
     категорії
    0.46
     செய்வத
    0.46
    ಮೊ
    0.46
    Activations Density 0.000%

    No Known Activations