© 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. 111607
    Prev
    Next
    INDEX
    Explanations

    images as inputs

    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
     Essex
    0.47
     Ch
    0.46
     K
    0.45
     IU
    0.45
     T
    0.44
     Oral
    0.43
     strict
    0.43
     sole
    0.43
     Nerd
    0.43
     Skip
    0.42
    POSITIVE LOGITS
    ｪ
    0.48
    embalikan
    0.48
    淈
    0.47
    垷
    0.47
     infraestructura
    0.46
    Precio
    0.45
    indahan
    0.45
    🏢
    0.45
    ichtigung
    0.44
    மானம்
    0.44
    Activations Density 0.024%

    No Known Activations