© 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. 168914
    Prev
    Next
    INDEX
    Explanations

    connection component

    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
    i
    0.51
    <start_of_image>
    0.49
    ↵
    0.47
    src
    0.45
    with
    0.45
    ly
    0.43
    待
    0.43
    妓
    0.43
    ste
    0.41
     tracks
    0.40
    POSITIVE LOGITS
    သွယ်
    0.58
    觡
    0.48
     حصے
    0.48
    砣
    0.47
     murmured
    0.46
    پوینت
    0.45
    䋆
    0.45
     ентите
    0.45
     감
    0.44
    ायचे
    0.44
    Activations Density 0.003%

    No Known Activations