© 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. 6394
    Prev
    Next
    INDEX
    Explanations

    quoting or highlighting words

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

    how and why questions

    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
    𝟐
    0.25
    ＆
    0.25
     elliptic
    0.24
    ・
    0.24
    을
    0.24
     [['
    0.24
     \[
    0.24
    QUrl
    0.23
     নারায়ণগঞ্জ
    0.23
    ⼀
    0.23
    POSITIVE LOGITS
     worldly
    0.26
    噱
    0.25
     picky
    0.25
    un
    0.24
    get
    0.24
     gimm
    0.24
     reali
    0.24
     bling
    0.23
    loser
    0.23
     civilized
    0.23
    Activations Density 0.107%

    No Known Activations