© 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. 104960
    Prev
    Next
    INDEX
    Explanations

    profit from, place, check

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

    spaceship pilot warnings shrine complete

    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
    TeXAtom
    0.47
    τσι
    0.45
    `.
    0.44
     Здравствуйте
    0.44
    +(
    0.43
    γν
    0.43
     UPC
    0.42
    ++.
    0.42
    Aluminum
    0.42
    .//
    0.42
    POSITIVE LOGITS
     enkel
    0.48
    부에
    0.46
    appendix
    0.44
     wybor
    0.44
    räume
    0.44
    ドラ
    0.43
     objections
    0.43
    शो
    0.43
    uterte
    0.43
    रील
    0.43
    Activations Density 0.000%

    No Known Activations