© 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. 152216
    Prev
    Next
    INDEX
    Explanations

    in or to

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

    languages, specific places

    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
    <
    0.49
     delve
    0.46
    (
    0.46
    </strong>
    0.43
    <strong>
    0.42
     constituents
    0.42
     Bora
    0.42
     heml
    0.42
     clothe
    0.41
     Sierra
    0.41
    POSITIVE LOGITS
    𝗈
    0.61
     lakini
    0.56
    ispiele
    0.54
     경기
    0.52
     すご
    0.51
    ᴏ
    0.51
     nhưng
    0.51
    𝘇
    0.51
    boek
    0.50
    𝓊
    0.50
    Activations Density 0.000%

    No Known Activations