© 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. 154316
    Prev
    Next
    INDEX
    Explanations

    quarter, leakage, reserves, delay

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

    described things about perception

    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
     supremac
    0.49
    ForRule
    0.48
    }:=
    0.47
     supremacist
    0.46
     dakkh
    0.45
     Kanpur
    0.45
    軽減
    0.45
     parâ
    0.43
    フィック
    0.43
    خستان
    0.43
    POSITIVE LOGITS
    </div>
    0.47
    mas
    0.47
    dé
    0.45
    uku
    0.45
    VAN
    0.45
    <0xA7>
    0.45
    am
    0.44
    綺麗な
    0.44
     μετα
    0.43
    <0x93>
    0.43
    Activations Density 0.000%

    No Known Activations