© 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. 54190
    Prev
    Next
    INDEX
    Explanations

    business and financial terms

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

    technical descriptions and processes

    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
     الوح
    0.48
    敝
    0.45
    ந்து
    0.44
     superconduct
    0.43
    んじゃない
    0.43
     accomplished
    0.43
    efois
    0.43
     depot
    0.43
    ັນ
    0.42
     hookah
    0.42
    POSITIVE LOGITS
     Signaling
    0.43
     Diameter
    0.42
    দেখে
    0.42
    引き続き
    0.42
    Xi
    0.42
    </h6>
    0.41
     Picture
    0.40
     messageFields
    0.40
     поез
    0.40
     Minas
    0.39
    Activations Density 0.001%

    No Known Activations