© 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. 48459
    Prev
    Next
    INDEX
    Explanations

    religious or legal contexts

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

    safety and problem solving

    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
    وا
    0.54
    ુર
    0.50
    Accord
    0.47
    ચર
    0.47
    는
    0.46
    Focused
    0.45
    棲
    0.45
    SpecID
    0.44
    ளும்
    0.44
    FRAME
    0.44
    POSITIVE LOGITS
    ÷
    0.49
    control
    0.47
     d
    0.46
    ght
    0.45
    iner
    0.45
    ricia
    0.45
    defin
    0.45
    öff
    0.45
     oft
    0.45
    defini
    0.44
    Activations Density 0.001%

    No Known Activations