© 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. 222496
    Prev
    Next
    INDEX
    Explanations

    finding convenience and setting

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

    disclaimers about jokes

    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
    ΠΑ
    0.47
     Variable
    0.46
    ش
    0.46
    nä
    0.46
    ANTES
    0.46
    چھ
    0.45
    কল্প
    0.45
     မြ
    0.45
     unterwegs
    0.45
    উর
    0.44
    POSITIVE LOGITS
     সকলেই
    0.48
    нин
    0.46
     be
    0.44
    镜
    0.43
    ání
    0.42
     समिति
    0.42
    дор
    0.42
    ření
    0.41
     संचालन
    0.41
    зыва
    0.41
    Activations Density 0.001%

    No Known Activations