© 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. 195975
    Prev
    Next
    INDEX
    Explanations

    religious texts, foreign languages, finance

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

    Okay, I won't

    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
    ുണ്ട
    0.54
     KSI
    0.48
    ണ്ഡ
    0.46
     Grammy
    0.42
    谓
    0.42
     listItem
    0.41
     marginBottom
    0.41
     riff
    0.40
    泷
    0.40
    可能是
    0.40
    POSITIVE LOGITS
    frees
    0.58
     प्रकाश
    0.55
    free
    0.54
    vocals
    0.54
    ष्ठ
    0.54
    finance
    0.53
    。<
    0.52
    financing
    0.52
    おく
    0.52
    cimentos
    0.51
    Activations Density 0.000%

    No Known Activations