© 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. 1539
    Prev
    Next
    INDEX
    Explanations

    XML declarations with utf-8 encoding

    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
    كلمنا
    0.34
    гене
    0.33
     取り
    0.32
     डेरिवेशन
    0.32
    ඡ
    0.31
    bica
    0.31
    limegreen
    0.31
     स्पून
    0.31
    𒆪
    0.31
    ówno
    0.30
    POSITIVE LOGITS
     however
    0.31
     revel
    0.29
    ave
    0.27
     însă
    0.27
     districts
    0.26
    astre
    0.26
     mountain
    0.26
     hr
    0.26
     tier
    0.26
    out
    0.25
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.