© 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. 138717
    Prev
    Next
    INDEX
    Explanations

    pictures listed with more details

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

    significant investment in AI

    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
    的な
    0.44
     sawtooth
    0.44
    して
    0.42
    orted
    0.42
     thistle
    0.41
    </h4>
    0.41
     hickory
    0.41
     pher
    0.40
    ק
    0.40
    >&
    0.40
    POSITIVE LOGITS
    все
    0.53
     Configuring
    0.53
    вол
    0.51
     Muham
    0.47
     tredje
    0.46
    лих
    0.46
    лых
    0.45
    there
    0.45
     Wochen
    0.45
    лын
    0.44
    Activations Density 0.002%

    No Known Activations