© 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. 240209
    Prev
    Next
    INDEX
    Explanations

    past experiences and future states

    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
    m
    0.55
    e
    0.50
    ip
    0.48
    r
    0.46
    and
    0.45
     Morrison
    0.45
    en
    0.44
    c
    0.44
     T
    0.44
    u
    0.44
    POSITIVE LOGITS
     scelto
    0.57
     autoWatch
    0.57
    分为
    0.54
     umowy
    0.52
    月底
    0.52
     bowiem
    0.52
     initialization
    0.52
     acabado
    0.52
    Parrocchia
    0.51
     początku
    0.51
    Activations Density 0.003%

    No Known Activations