© 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. 132093
    Prev
    Next
    INDEX
    Explanations

    Local and principal titles

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

    explaining or describing something

    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
    }$&$
    0.52
     자기
    0.48
    繖
    0.46
     〢
    0.45
    넝
    0.44
    𝖠
    0.44
    }$&$-
    0.43
    窘
    0.43
    筮
    0.43
     Cliente
    0.42
    POSITIVE LOGITS
    v
    0.55
    4
    0.51
    rc
    0.49
     grounded
    0.46
    eries
    0.45
     accrued
    0.44
    ($
    0.44
    iler
    0.44
     taxes
    0.44
     patriotic
    0.44
    Activations Density 0.000%

    No Known Activations