© 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. 3798
    Prev
    Next
    INDEX
    Explanations

    b1

    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
    ోతి
    0.43
    <unused27>
    0.41
    शिवाय
    0.40
     ولم
    0.40
    
    0.40
     או
    0.39
    อื่น
    0.39
    icrob
    0.39
     化粧
    0.39
    كم
    0.38
    POSITIVE LOGITS
     c
    0.50
     time
    0.46
     des
    0.46
     Nights
    0.44
    T
    0.44
     defined
    0.42
     b
    0.41
    b
    0.40
     real
    0.40
    text
    0.39
    Activations Density 0.004%

    No Known Activations