© 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. 111425
    Prev
    Next
    INDEX
    Explanations

    know about

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

    project hosting, remember vividly, re.sub

    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
     kö
    0.51
     rhiz
    0.46
    thal
    0.45
    rital
    0.45
     gost
    0.44
     Shown
    0.43
    ³
    0.43
    рија
    0.42
     beruf
    0.42
     valam
    0.42
    POSITIVE LOGITS
    GEBURTS
    0.52
    ILIA
    0.52
    ז
    0.49
    DEFIN
    0.48
    に入れ
    0.48
    欱
    0.46
    विज्ञान
    0.45
    NAME
    0.45
    Ú
    0.45
    FAILURE
    0.45
    Activations Density 0.000%

    No Known Activations