© 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. 209248
    Prev
    Next
    INDEX
    Explanations

    savings on

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

    capacity, freedom, power, position, means

    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
    ك
    0.49
     وفر
    0.48
     па
    0.47
    艮
    0.46
    가능
    0.45
     DECIMAL
    0.45
     ¶
    0.45
     е
    0.45
     gobern
    0.44
     التس
    0.44
    POSITIVE LOGITS
    7
    0.50
    very
    0.47
    iyev
    0.46
    hung
    0.45
     असं
    0.44
    いです
    0.43
    9
    0.43
    inafter
    0.43
    4
    0.43
    at
    0.42
    Activations Density 0.000%

    No Known Activations