© 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. 66412
    Prev
    Next
    INDEX
    Explanations

    title construction underlying usually size company bill fewer

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

    obfuscation techniques

    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
    ↵
    0.47
     mengaj
    0.43
    이트
    0.42
    яв
    0.40
    流入
    0.39
    ש
    0.38
     select
    0.38
     TEACH
    0.38
    日
    0.38
    ить
    0.38
    POSITIVE LOGITS
     lézards
    0.51
     admits
    0.48
     čty
    0.46
    rée
    0.46
     Gör
    0.45
     워
    0.44
    odhya
    0.44
    ément
    0.44
     éton
    0.44
    ház
    0.44
    Activations Density 0.001%

    No Known Activations