© 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. 70277
    Prev
    Next
    INDEX
    Explanations

    beginning of phrases

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

    approving requests or conditions

    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
     тему
    0.51
    혜
    0.50
     Franc
    0.46
     Wagon
    0.46
    и
    0.44
    ⟋
    0.44
     chất
    0.44
     siedz
    0.43
     Moskau
    0.43
     Wishes
    0.42
    POSITIVE LOGITS
     autonom
    0.43
    ੰ
    0.43
    通行
    0.42
    肅
    0.40
     autonomous
    0.40
    oringa
    0.40
     소비
    0.39
     CONSUM
    0.39
     halves
    0.39
     unofficial
    0.38
    Activations Density 0.000%

    No Known Activations