© 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. 29190
    Prev
    Next
    INDEX
    Explanations

    question marks and exclamations

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

    looking for

    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
    如有
    0.45
     ততই
    0.42
    佷
    0.41
     кстати
    0.41
    伈
    0.40
    нії
    0.39
     అది
    0.38
    ๒
    0.38
     النظر
    0.38
    мих
    0.37
    POSITIVE LOGITS
    ?!
    1.28
    ？
    1.24
    ?
    1.22
    ?!?
    1.19
    ?'
    1.16
    !?
    1.16
    ؟
    1.16
    ?...
    1.15
    ?!?!
    1.14
    ?"
    1.13
    Activations Density 0.058%

    No Known Activations