© 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. 191756
    Prev
    Next
    INDEX
    Explanations

    never perform

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

    scale, states, and processes

    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
    umin
    0.52
    less
    0.50
    高
    0.45
    Ｇ
    0.44
    听
    0.43
     app
    0.42
    （
    0.42
     hi
    0.42
    flexible
    0.42
     k
    0.41
    POSITIVE LOGITS
     célula
    0.54
     energético
    0.48
     клеток
    0.48
     remerc
    0.48
     ENEM
    0.48
    ção
    0.47
    ாலிக
    0.47
    یط
    0.46
    راجعه
    0.46
     அவர்களுக்கு
    0.46
    Activations Density 0.000%

    No Known Activations