© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126274
    Prev
    Next
    INDEX
    Explanations

    into yourbrakenominatingowned

    np_acts-logits-general · gemini-2.5-flash-lite

    LinkedIn profile related information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parrot
    0.52
     parrots
    0.48
    o
    0.47
    extreme
    0.45
     gant
    0.44
    ing
    0.44
    ermost
    0.44
    ed
    0.44
    vans
    0.44
     freshness
    0.43
    POSITIVE LOGITS
    伈
    0.56
    ঘাত
    0.49
    cké
    0.49
    靕
    0.47
     comptes
    0.46
    紧急
    0.45
    ografía
    0.45
    चारी
    0.44
     écoles
    0.44
    CIES
    0.44
    Activations Density 0.000%

    No Known Activations