© 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. 145557
    Prev
    Next
    INDEX
    Explanations

    compensation for damages

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

    instructions or annotations

    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
    ியாக
    0.47
     dragState
    0.45
    мыс
    0.44
    ༦
    0.44
     gsi
    0.43
    гна
    0.43
     ఇటీ
    0.43
    뤘
    0.43
    ल्ल्या
    0.42
     récentes
    0.42
    POSITIVE LOGITS
    ਨ
    0.48
     deberá
    0.46
    MORPH
    0.46
    製造
    0.46
    울
    0.45
    o
    0.45
    原因
    0.44
    ந்திர
    0.43
    発電
    0.43
     ಔಷಧ
    0.42
    Activations Density 0.001%

    No Known Activations