© 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. 16-GEMMASCOPE-2-RES-262K
    7. 138157
    Prev
    Next
    INDEX
    Explanations

    matrix effect, capture, position

    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_16_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
     abbia
    0.54
     mickey
    0.49
     бло
    0.47
     茶
    0.46
    IFIER
    0.46
     梅
    0.46
     blat
    0.45
     henna
    0.45
     akh
    0.45
     amerikan
    0.44
    POSITIVE LOGITS
    vital
    0.50
     Disbursement
    0.48
     शोषण
    0.47
     neutralize
    0.47
     neutralization
    0.46
     quantification
    0.46
     incentivize
    0.45
    essence
    0.45
    angels
    0.45
    "};
    0.44
    Activations Density 0.001%

    No Known Activations