© 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. 33923
    Prev
    Next
    INDEX
    Explanations

    performing actions or tasks

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

    took over from

    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
     접근
    0.47
    不存在
    0.46
    郗
    0.44
     Maarten
    0.43
    кта
    0.41
     kein
    0.40
    ктора
    0.40
    _{+}-
    0.40
    不会
    0.40
     ठहर
    0.39
    POSITIVE LOGITS
    six
    0.45
    success
    0.44
    ab
    0.44
     kal
    0.44
    od
    0.43
    handsome
    0.43
    sar
    0.43
     suits
    0.42
    single
    0.42
     ചെയ്യുന്നു
    0.41
    Activations Density 0.000%

    No Known Activations