© 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. 66036
    Prev
    Next
    INDEX
    Explanations

    phase stages and steps

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

    phase, Phase 1, phase changes

    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
    a
    0.82
    t
    0.75
    tamil
    0.69
    switching
    0.65
     सांगितलं
    0.65
    el
    0.64
    set
    0.63
    seem
    0.62
    hol
    0.62
    offsetof
    0.61
    POSITIVE LOGITS
    ’
    0.88
     ph
    0.84
     PH
    0.84
     PHA
    0.82
    ли
    0.80
     Phar
    0.78
     phal
    0.77
     phon
    0.77
     phe
    0.75
     Pharaoh
    0.73
    Activations Density 0.216%

    No Known Activations