© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 136283
    Prev
    Next
    INDEX
    Explanations

    section titles and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arrerol
    0.54
    silk
    0.53
     naturelles
    0.52
    risque
    0.50
    notebook
    0.48
    tekn
    0.47
     შეიძ
    0.47
    𝓭
    0.47
    కరించ
    0.47
    嘍
    0.47
    POSITIVE LOGITS
    a
    0.52
     *
    0.49
     a
    0.49
    ];
    0.48
     also
    0.46
    );
    0.46
     Also
    0.45
     önce
    0.44
     Comparator
    0.44
     dereg
    0.44
    Activations Density 0.002%

    No Known Activations