© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 31433
    Prev
    Next
    INDEX
    Explanations

    functions, jobs, value, stage, driving

    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
    Һ
    0.49
    '].
    0.48
    Repost
    0.48
    అ
    0.48
    )}')
    0.48
    H
    0.48
     Auswahl
    0.47
    М
    0.47
     Angeb
    0.47
    '}
    0.47
    POSITIVE LOGITS
    kernels
    0.49
     drifting
    0.45
     fertilized
    0.44
     structural
    0.44
    structural
    0.44
     truffle
    0.44
     scented
    0.43
     fertile
    0.42
     certos
    0.42
    力量
    0.42
    Activations Density 0.000%

    No Known Activations