© 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. 189184
    Prev
    Next
    INDEX
    Explanations

    specifying errors or details

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

    convert all

    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
    sh
    0.47
    mla
    0.46
    つまり
    0.45
    S
    0.44
    gt
    0.43
     sil
    0.43
    ecta
    0.43
    expert
    0.42
     cauliflower
    0.42
    ",$
    0.41
    POSITIVE LOGITS
    vykor
    0.57
    ㄾ
    0.48
    setClass
    0.47
    instellung
    0.47
    炘
    0.46
    น์โหลด
    0.46
    ISPW
    0.45
    錒
    0.45
     phasor
    0.44
     एकूण
    0.44
    Activations Density 0.000%

    No Known Activations