© 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. 84674
    Prev
    Next
    INDEX
    Explanations

    component or module files

    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
    Directive
    0.43
    athermy
    0.42
    Polic
    0.42
    έα
    0.42
    蚬
    0.40
    বন্ত
    0.39
     directive
    0.38
    umia
    0.38
    Rail
    0.38
     फैन
    0.38
    POSITIVE LOGITS
     reservoirs
    0.38
    =+
    0.37
     Convenient
    0.37
     Northeastern
    0.37
     относительно
    0.36
     dichloromethane
    0.36
     той
    0.36
     আকাশের
    0.35
     Delicious
    0.35
     gentil
    0.35
    Activations Density 0.001%

    No Known Activations