Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 7636
    Prev
    Next
    INDEX
    Explanations

    void and admitted

    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
     A
    0.60
     a
    0.59
    Offsets
    0.57
    అ
    0.55
    ଅ
    0.54
     ")
    0.54
     એ
    0.52
     s
    0.52
     അവന്റെ
    0.52
     ലെ
    0.51
    POSITIVE LOGITS
    ㅝ
    0.48
    db
    0.46
    ness
    0.45
     geographical
    0.45
     mỗi
    0.45
     guided
    0.44
    ният
    0.44
    地方
    0.44
    ным
    0.42
     contribution
    0.42
    Activations Density 0.000%

    No Known Activations