© 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. 164969
    Prev
    Next
    INDEX
    Explanations

    flight arrangement repairs

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

    biological functions, actions

    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
    (/^
    0.46
    father
    0.45
    ંદ્ર
    0.44
    يبه
    0.44
    ابة
    0.43
    abria
    0.43
    他們
    0.42
    emoji
    0.42
     Taxes
    0.42
    अब
    0.42
    POSITIVE LOGITS
     사용하는
    0.48
     기
    0.46
    ს
    0.44
     논
    0.43
     능
    0.43
     사용할
    0.43
     স্ব
    0.42
     사건
    0.41
     학교
    0.41
    cic
    0.41
    Activations Density 0.000%

    No Known Activations