© 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. 175149
    Prev
    Next
    INDEX
    Explanations

    stated otherwise

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

    focused on

    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
    raad
    0.46
    ᱹ
    0.44
    ደን
    0.44
    Muy
    0.43
     मानसून
    0.43
     Prospective
    0.43
    ೭
    0.42
    捜
    0.41
    Performance
    0.41
    Anti
    0.41
    POSITIVE LOGITS
    กลุ่ม
    0.51
     tipi
    0.49
     oldest
    0.46
     özellikleri
    0.45
     pemimpin
    0.45
     tipo
    0.44
     coppia
    0.44
    کرین
    0.44
    🐥
    0.44
    PhotoMode
    0.43
    Activations Density 0.002%

    No Known Activations