© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 137230
    Prev
    Next
    INDEX
    Explanations

    account each, launch timeframe

    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
    
    0.46
    lectoral
    0.46
    IDF
    0.45
    分岐
    0.45
    ネットワーク
    0.44
    專輯
    0.44
    ἢ
    0.44
    ᚗ
    0.44
    \<^
    0.43
    )]^{
    0.43
    POSITIVE LOGITS
     Don
    0.50
     Isn
    0.48
     It
    0.43
    ate
    0.42
     only
    0.42
     Tempor
    0.41
     always
    0.40
     as
    0.40
     Th
    0.40
     it
    0.40
    Activations Density 0.007%

    No Known Activations