© 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. 31-GEMMASCOPE-2-RES-262K
    7. 5773
    Prev
    Next
    INDEX
    Explanations

    needs, expectations, and abstract concepts

    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
    7
    0.32
    5
    0.31
    4
    0.29
    <0x80>
    0.29
    8
    0.27
    r
    0.27
    9
    0.26
    2
    0.26
    3
    0.26
    6
    0.25
    POSITIVE LOGITS
     whatnot
    0.35
     downright
    0.29
     التي
    0.29
     refusal
    0.29
     נ
    0.27
     ganas
    0.27
     heartache
    0.26
     എല്ലാം
    0.26
     ஏன்
    0.25
     ت
    0.25
    Activations Density 0.420%

    No Known Activations