© 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. 18502
    Prev
    Next
    INDEX
    Explanations

    accessing digital content

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

    asking questions, giving examples, explaining

    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
     inú
    0.49
    µ
    0.49
    Lors
    0.47
     coexist
    0.44
    σο
    0.43
    φε
    0.43
     fluctuate
    0.43
     fluctu
    0.43
    Σ
    0.43
     qualify
    0.42
    POSITIVE LOGITS
     Meanwhile
    0.42
    angelo
    0.42
    anwhile
    0.41
    冝
    0.38
    raving
    0.38
     సినిమాలో
    0.38
    ating
    0.37
    ayan
    0.37
     Chances
    0.37
     meanwhile
    0.37
    Activations Density 0.000%

    No Known Activations