© 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. 31781
    Prev
    Next
    INDEX
    Explanations

    Albert E. in open pot

    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
     (
    0.43
     \[
    0.43
    �
    0.43
     �
    0.42
     Achilles
    0.41
    </b>
    0.40
     ($
    0.39
     Azores
    0.38
     aud
    0.38
     co
    0.37
    POSITIVE LOGITS
    Feedback
    0.45
    헿
    0.42
     에서
    0.42
    Synced
    0.41
    มาย
    0.41
    是的
    0.41
    이다
    0.40
    Allora
    0.39
    Bew
    0.39
    ত্যাশিত
    0.39
    Activations Density 0.008%

    No Known Activations