© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 113415
    Prev
    Next
    INDEX
    Explanations

    change or modify

    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
    \|$.
    0.50
    chod
    0.49
    Nicht
    0.48
    разде
    0.47
     основном
    0.47
     berdoa
    0.47
     буду
    0.46
     предлага
    0.46
    तिहास
    0.46
     биз
    0.46
    POSITIVE LOGITS
     Vaccine
    0.49
    ,
    0.45
     sunny
    0.43
     vaccine
    0.43
     DAMAGES
    0.43
     Drupal
    0.42
     vaccin
    0.41
    ële
    0.41
     Newspapers
    0.41
     HI
    0.41
    Activations Density 0.001%

    No Known Activations