© 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. 35637
    Prev
    Next
    INDEX
    Explanations

    in this case, thank you, New York

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

    comparison or function

    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
     pdelay
    0.46
     серде
    0.44
     //}
    0.43
     αφού
    0.42
     afterthought
    0.42
     >>>
    0.42
     esté
    0.42
     commutator
    0.42
    ลล์
    0.42
     STEP
    0.41
    POSITIVE LOGITS
    ساز
    0.45
    دهای
    0.45
     اقسام
    0.44
     gruppi
    0.43
     வளர்ச்ச
    0.43
     serius
    0.43
    gru
    0.42
    猟
    0.42
    वर्ग
    0.42
     मोठे
    0.42
    Activations Density 0.000%

    No Known Activations