© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91117
    Prev
    Next
    INDEX
    Explanations

    hypothetical situations and shared content

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

    represented by, is bound, activated if

    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
    Negative Logits
    ️⃣
    0.48
    Merc
    0.46
    alted
    0.46
    iggers
    0.44
    omia
    0.44
    aned
    0.44
    ig
    0.44
    },
    0.44
    nton
    0.43
    odora
    0.43
    POSITIVE LOGITS
    値
    0.52
    イ
    0.51
     EVIDENCE
    0.50
    その他の
    0.49
    ﾛ
    0.49
    レ
    0.49
    ジャン
    0.48
    同時に
    0.48
    𝖑
    0.48
    値を
    0.47
    Activations Density 0.001%

    No Known Activations