© 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. 113084
    Prev
    Next
    INDEX
    Explanations

    discussion of pros and cons

    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
     pastes
    0.55
    {
    0.50
     muscle
    0.49
     tats
    0.48
    নিজের
    0.46
     motivates
    0.46
    <
    0.44
    '
    0.44
    ყო
    0.43
     марке
    0.42
    POSITIVE LOGITS
    wissenschaft
    0.45
    鴻
    0.43
     כי
    0.42
    Science
    0.41
     इश्क
    0.41
    วิทยา
    0.41
     أصبح
    0.40
    晫
    0.40
     لاہور
    0.39
     irrever
    0.39
    Activations Density 0.005%

    No Known Activations