© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 14361
    Prev
    Next
    INDEX
    Explanations

    how many/expect thunderstorms/pitching well

    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_40_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
     snowing
    0.41
    पणे
    0.39
    丁目
    0.39
     matur
    0.39
     platz
    0.38
    ორე
    0.36
    두
    0.36
    Cha
    0.36
    żeli
    0.36
    Ch
    0.36
    POSITIVE LOGITS
     racked
    0.41
    developers
    0.41
     boosted
    0.41
     ApiException
    0.41
    損失
    0.41
    犯
    0.41
     unsurprisingly
    0.40
     pharmaceuticals
    0.40
    Ｏ
    0.40
    ਾਸ
    0.39
    Activations Density 0.000%

    No Known Activations