© 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. 28341
    Prev
    Next
    INDEX
    Explanations

    parallel to

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

    directed to

    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
     garnered
    0.42
    ཟ
    0.42
    仅仅
    0.40
     нового
    0.39
     диапазо
    0.39
     कलर
    0.38
     розпо
    0.38
    𝘇
    0.38
     realistically
    0.38
     নানান
    0.38
    POSITIVE LOGITS
    แต่
    0.40
    但不
    0.39
    }:=\
    0.39
    を変更
    0.38
    legraf
    0.38
    USART
    0.37
     ون
    0.37
    And
    0.36
     DIG
    0.36
    Understand
    0.36
    Activations Density 0.034%

    No Known Activations