© 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. 25845
    Prev
    Next
    INDEX
    Explanations

    legal and financial terms

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

    one side is perpetually

    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
    in
    0.53
    i
    0.52
    es
    0.49
    maine
    0.49
     Paola
    0.48
    ent
    0.47
    Up
    0.46
     Christian
    0.45
    lardan
    0.45
    lara
    0.44
    POSITIVE LOGITS
    ασία
    0.48
     quantidades
    0.45
    畳
    0.45
    ্বাস
    0.45
     canaux
    0.45
    效率
    0.45
    原則
    0.45
    含量
    0.44
    困難
    0.44
    اہم
    0.44
    Activations Density 0.001%

    No Known Activations