© 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. 44530
    Prev
    Next
    INDEX
    Explanations

    future plans for Iran

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

    conjunctions and exceptions

    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
     کرد
    0.57
    𝘵
    0.55
    <unused345>
    0.55
    ഓ
    0.53
    <unused654>
    0.52
     был
    0.52
     были
    0.52
     został
    0.52
    <unused2013>
    0.52
     વિ
    0.51
    POSITIVE LOGITS
    zo
    0.48
    participants
    0.48
    monia
    0.46
     participants
    0.45
    ERRY
    0.45
     airplanes
    0.45
     affiliates
    0.44
     roofs
    0.44
    iden
    0.44
    bern
    0.44
    Activations Density 0.000%

    No Known Activations