© 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. 218630
    Prev
    Next
    INDEX
    Explanations

    locations and specific terms

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

    Brand Foundation

    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
    TA
    0.48
    ING
    0.48
    TOD
    0.48
     本
    0.47
    ，
    0.47
    AR
    0.47
    GA
    0.46
    Φ
    0.46
    HAND
    0.45
     あの
    0.45
    POSITIVE LOGITS
     Trend
    0.50
    renched
    0.44
    iall
    0.44
    ್ರಿ
    0.43
    Trend
    0.43
     Три
    0.41
     Sainsbury
    0.41
     pigmented
    0.40
    IRED
    0.40
     Seminary
    0.39
    Activations Density 0.000%

    No Known Activations