© 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. 182461
    Prev
    Next
    INDEX
    Explanations

    certain words followed by details

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

    represents or defines concepts

    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
    blogs
    0.54
     Consideration
    0.48
    ⟤
    0.47
    elä
    0.46
    mér
    0.46
    oying
    0.46
    frmt
    0.44
    baka
    0.44
    ahlt
    0.44
    hees
    0.44
    POSITIVE LOGITS
    I
    0.54
    이
    0.47
    Ξ
    0.43
    ला
    0.43
    가
    0.42
     determinada
    0.42
    お
    0.42
    옵
    0.42
    Il
    0.42
    II
    0.42
    Activations Density 0.000%

    No Known Activations