© 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. 223753
    Prev
    Next
    INDEX
    Explanations

    description words

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

    purpose, existing, equity, or control

    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
     Präsident
    0.52
    眎
    0.50
    垍
    0.50
    assertThat
    0.49
    上限
    0.48
     প্রেসিডেন্ট
    0.47
    αιν
    0.46
    avoz
    0.46
     voci
    0.46
    SourceName
    0.45
    POSITIVE LOGITS
    rograph
    0.49
    This
    0.46
     ]
    0.46
     ditch
    0.46
    JP
    0.45
     ۴
    0.45
     ۲
    0.44
    Mr
    0.44
    What
    0.43
    Fr
    0.43
    Activations Density 0.000%

    No Known Activations