© 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. 131192
    Prev
    Next
    INDEX
    Explanations

    English translation

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

    Imperial, Western, Ukraine, UserId, encompassing

    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
    шта
    0.50
    rawdę
    0.49
    routerProps
    0.49
    รวจ
    0.47
    рыма
    0.46
    ㄼ
    0.46
    संहार
    0.45
    RichEmbed
    0.45
     InputAction
    0.44
    archiwizowane
    0.43
    POSITIVE LOGITS
     combinatorial
    0.54
     reduction
    0.51
     preferences
    0.50
     frequ
    0.50
     suffix
    0.50
     a
    0.48
     mathematics
    0.48
     substitution
    0.48
     suffixes
    0.48
     mathemat
    0.47
    Activations Density 0.001%

    No Known Activations