© 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. 156489
    Prev
    Next
    INDEX
    Explanations

    options and choices

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

    colon or asterisk followed by text

    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
    ல
    0.46
    發表
    0.45
    Κ
    0.44
    Commit
    0.44
    kowe
    0.44
    стье
    0.44
    kker
    0.44
    Manifest
    0.44
    推理
    0.44
    য়
    0.43
    POSITIVE LOGITS
    еш
    0.48
    ocont
    0.48
    }^{*},
    0.48
     그는
    0.47
     ie
    0.47
     সামনে
    0.46
    она
    0.46
     осозна
    0.46
     strani
    0.45
     unfamiliar
    0.45
    Activations Density 0.000%

    No Known Activations