© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 151326
    Prev
    Next
    INDEX
    Explanations

    common phrases

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

    specific phrase association

    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
     ма
    0.53
    ิทธิ์
    0.53
    یک
    0.52
    ร์
    0.52
    ือ
    0.51
     ज्ये
    0.50
    TAS
    0.49
    ็
    0.48
    GENER
    0.48
    aktur
    0.48
    POSITIVE LOGITS
    forall
    0.46
     Academia
    0.43
     DX
    0.43
     શિક્ષણ
    0.42
     Curious
    0.42
     중간
    0.41
    λογή
    0.41
    인지
    0.40
     Optimum
    0.39
    rom
    0.39
    Activations Density 0.000%

    No Known Activations