© 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. 177722
    Prev
    Next
    INDEX
    Explanations

    parable credit in approved

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

    competition, creators, and hacks

    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
     রহমানের
    0.51
     vacaciones
    0.49
     vaginale
    0.49
     acceptor
    0.49
     passivation
    0.47
    NaF
    0.47
     manipulation
    0.46
    𒉌
    0.46
     উভয়ে
    0.45
     solub
    0.45
    POSITIVE LOGITS
    r
    0.66
    t
    0.58
    ot
    0.57
    v
    0.57
    k
    0.54
    ta
    0.54
    ted
    0.48
    bris
    0.46
    ，
    0.46
    ol
    0.46
    Activations Density 0.001%

    No Known Activations