© 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. 22405
    Prev
    Next
    INDEX
    Explanations

    new announcements or launches

    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
    जब
    0.49
    受到
    0.47
    {\'
    0.47
    apayati
    0.46
     labile
    0.46
     возмо
    0.46
    𝚙
    0.46
    遇到
    0.45
    受
    0.45
     nuovamente
    0.45
    POSITIVE LOGITS
    0.61
     lancement
    0.55
     लॉन्च
    0.52
     lancio
    0.52
     Launch
    0.51
    -
    0.48
     Premier
    0.47
     Lien
    0.46
     launch
    0.46
     Weise
    0.46
    Activations Density 0.005%

    No Known Activations