© 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. 64575
    Prev
    Next
    INDEX
    Explanations

    sanctuary trek, cannabis seeds

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

    5 stars

    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
    chr
    0.61
    g
    0.58
    b
    0.57
    d
    0.54
    v
    0.54
    Shift
    0.50
    Paste
    0.49
    bcc
    0.49
    c
    0.49
    indeterminate
    0.49
    POSITIVE LOGITS
    ောင့်
    0.49
     atributos
    0.49
     oblasti
    0.48
    澳洲
    0.45
     renom
    0.44
    zoek
    0.44
     opiek
    0.43
     végétation
    0.43
     параметров
    0.42
     estaven
    0.42
    Activations Density 0.000%

    No Known Activations