© 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. 40-GEMMASCOPE-2-RES-262K
    4. 120281
    Prev
    Next
    INDEX
    Explanations

    smart advice

    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_40_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
    P
    0.42
    onset
    0.41
    Onset
    0.41
    quoted
    0.39
    ek
    0.38
    нев
    0.38
    G
    0.37
    ø
    0.37
    فور
    0.37
     lø
    0.36
    POSITIVE LOGITS
     района
    0.42
     Fuente
    0.41
     etiquetas
    0.40
     Madeira
    0.40
     ιστο
    0.40
    ΙΑ
    0.40
     Sierra
    0.38
    惭
    0.38
     ശേഖ
    0.38
    蕞
    0.38
    Activations Density 0.000%

    No Known Activations