© 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. 173472
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific words and what follows

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

    penalties, diffusion models, available index

    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
    continue
    0.48
    ণীর
    0.47
     counsel
    0.45
    i
    0.45
    ogn
    0.44
    JSON
    0.44
    flows
    0.42
    BAR
    0.42
     Hours
    0.41
    闱
    0.41
    POSITIVE LOGITS
     انك
    0.49
     జ
    0.47
     eerie
    0.44
     принадле
    0.43
     öld
    0.43
     تعدى
    0.42
    映画
    0.41
    装備
    0.41
     nggak
    0.41
     desconoc
    0.40
    Activations Density 0.000%

    No Known Activations