© 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. 14339
    Prev
    Next
    INDEX
    Explanations

    programming constructs and contexts

    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
    Regards
    0.38
    வையாக
    0.37
     délais
    0.37
    <unused371>
    0.36
    ństwo
    0.35
    Amat
    0.35
     terme
    0.34
     resTmp
    0.34
     stature
    0.34
    𝐭
    0.33
    POSITIVE LOGITS
     sake
    1.20
     purposes
    0.96
     Sake
    0.83
     Purposes
    0.64
    来说
    0.52
    來說
    0.52
     ump
    0.52
     reasons
    0.50
     ول
    0.49
     afin
    0.48
    Activations Density 0.008%

    No Known Activations