© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 130455
    Prev
    Next
    INDEX
    Explanations

    type in various languages

    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
     frightened
    0.37
     संज्ञा
    0.37
     defens
    0.36
    च्छ
    0.35
     Join
    0.33
     purpos
    0.33
    ˵
    0.33
    ած
    0.33
     Carole
    0.33
    actoring
    0.33
    POSITIVE LOGITS
     type
    0.76
    type
    0.71
     типу
    0.65
     типа
    0.63
     tipo
    0.58
    タイプの
    0.58
     typu
    0.56
     પ્રકાર
    0.55
     نوع
    0.55
    型
    0.54
    Activations Density 0.000%

    No Known Activations