© 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. 16-GEMMASCOPE-2-RES-262K
    4. 11467
    Prev
    Next
    INDEX
    Explanations

    factor analysis association hierarchy

    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_16_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
     الَّذ
    0.59
     گول
    0.57
    ُونَ
    0.57
     než
    0.57
    बर्ग
    0.57
    !";
    0.57
     ዓይነት
    0.57
    বার্গ
    0.56
     acteur
    0.55
     !"
    0.55
    POSITIVE LOGITS
     Fecha
    0.66
     Kim
    0.64
     Pelle
    0.63
     Esp
    0.61
     Bali
    0.60
     Palacio
    0.59
     Ard
    0.57
     Lisbon
    0.57
    ັ
    0.55
     McC
    0.55
    Activations Density 0.020%

    No Known Activations