© 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. 103551
    Prev
    Next
    INDEX
    Explanations

    glued to phone or smoke test

    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
     r
    0.61
     User
    0.57
     National
    0.56
     FREE
    0.55
     $
    0.54
     Zugriff
    0.54
     Wild
    0.53
     Unified
    0.53
     ztr
    0.53
     NaN
    0.53
    POSITIVE LOGITS
    when
    0.57
    ployment
    0.57
    ニュ
    0.57
    わからない
    0.55
    ਮ
    0.54
    Casey
    0.54
    オ
    0.53
    O
    0.52
    ଞ
    0.52
    それ
    0.52
    Activations Density 0.000%

    No Known Activations