© 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. 155007
    Prev
    Next
    INDEX
    Explanations

    found sheep

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

    no native Linux versions

    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
    ﺼ
    0.55
    ﻜ
    0.51
    Appending
    0.48
    reported
    0.47
    appending
    0.46
    Heating
    0.46
    Correction
    0.46
    ﻤ
    0.45
     stirring
    0.45
    濬
    0.43
    POSITIVE LOGITS
    ل
    0.63
     automáticamente
    0.51
     Fernández
    0.50
     SVP
    0.50
     directamente
    0.50
    㞰
    0.50
     ETF
    0.49
     lighthouse
    0.49
     pabb
    0.48
     TPS
    0.48
    Activations Density 0.001%

    No Known Activations