© 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. 36312
    Prev
    Next
    INDEX
    Explanations

    issued report

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

    explanationbecause it, secret lair, not supported, sequencer

    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
    ুনা
    0.44
    waste
    0.44
     waste
    0.40
    ők
    0.40
    gutter
    0.39
    ଜ
    0.39
    spaper
    0.39
    βέρ
    0.39
    result
    0.38
    滓
    0.38
    POSITIVE LOGITS
     često
    0.52
     meditative
    0.52
     بسیار
    0.51
     espress
    0.50
     अत्यंत
    0.47
    และความ
    0.47
     ((
    0.46
     بہت
    0.46
     omnip
    0.46
     ความ
    0.45
    Activations Density 0.001%

    No Known Activations