© 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. 15578
    Prev
    Next
    INDEX
    Explanations

    Russian and Hebrew characters

    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
     proporcional
    0.40
    ↵↵
    0.36
     using
    0.34
     được
    0.34
     prices
    0.33
     daher
    0.33
     use
    0.32
     wyb
    0.32
     servers
    0.32
     itr
    0.32
    POSITIVE LOGITS
    Й
    0.49
    ול
    0.46
    ста
    0.45
     истори
    0.45
    ִ
    0.44
    לי
    0.44
     концеп
    0.43
    по
    0.42
    ascin
    0.42
    וּ
    0.42
    Activations Density 0.111%

    No Known Activations