© 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-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 1819
    Prev
    Next
    INDEX
    Explanations

    the followed by specific descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
     realizado
    1.08
    㕶
    0.92
     realizada
    0.91
    ㅝ
    0.89
     realizadas
    0.89
     конф
    0.89
     ocorreu
    0.89
     realização
    0.86
     importância
    0.85
     houve
    0.85
    POSITIVE LOGITS
    (
    0.95
     or
    0.93
     (
    0.89
    or
    0.87
     rarely
    0.86
     relatively
    0.85
     often
    0.82
     small
    0.78
    이나
    0.75
     tightly
    0.74
    Activations Density 0.001%

    No Known Activations