© 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. 60895
    Prev
    Next
    INDEX
    Explanations

    raw material, next time

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

    pseud, art, nonce

    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
     stressed
    0.55
    stressed
    0.47
    0
    0.47
     extremo
    0.46
    resso
    0.46
     simplices
    0.45
    っ
    0.45
    iertas
    0.45
    oit
    0.45
    ković
    0.45
    POSITIVE LOGITS
    缫
    0.46
     bureaucratic
    0.44
    锁
    0.44
    Tout
    0.43
     ग्राउंड
    0.42
    墉
    0.42
    Mou
    0.42
     hydrodynamic
    0.42
    جواب
    0.40
    бурга
    0.39
    Activations Density 0.000%

    No Known Activations