© 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. 122375
    Prev
    Next
    INDEX
    Explanations

    text and other specific nouns

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

    reminders and notes

    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
     തീ
    0.45
     წ
    0.45
     lordship
    0.44
     Godfather
    0.44
     വിഷയ
    0.43
     နဲ့
    0.43
     nationwide
    0.42
    чая
    0.42
     серде
    0.42
    ற்றும்
    0.41
    POSITIVE LOGITS
    片
    0.55
    ifolds
    0.49
    デ
    0.49
    <0x0D>
    0.47
    кономі
    0.46
    dx
    0.44
    敏
    0.44
    dain
    0.44
    odimensional
    0.44
    我
    0.44
    Activations Density 0.001%

    No Known Activations