© 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. 34329
    Prev
    Next
    INDEX
    Explanations

    emoticons like :D and :cry:

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

    speech or descriptive parentheticals

    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
     ?:
    0.54
    ?:
    0.47
    ?.
    0.46
     Qxh
    0.45
     ppl
    0.45
     terá
    0.43
    %:
    0.43
     ():
    0.42
     Utilis
    0.42
    ષ્ય
    0.42
    POSITIVE LOGITS
    poison
    0.42
     prestaciones
    0.41
    em
    0.41
     curve
    0.41
     ragged
    0.40
    ר
    0.40
     nudge
    0.40
    analog
    0.39
    hardhat
    0.39
    লেম
    0.39
    Activations Density 0.001%

    No Known Activations