© 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. 145247
    Prev
    Next
    INDEX
    Explanations

    susceptible to other things

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

    specific qualifiers and descriptions

    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
     sidewalks
    0.52
     Kxh
    0.51
    いました
    0.49
     pecans
    0.49
    ज्ञात
    0.49
    }+\
    0.49
    पीरियंस
    0.49
    ファイルを
    0.48
     অক্স
    0.48
     tragedies
    0.48
    POSITIVE LOGITS
     engine
    0.47
    还没
    0.44
    writer
    0.44
    estan
    0.42
    ற்ச
    0.42
    诠
    0.42
     train
    0.40
     pur
    0.40
     plant
    0.40
    ёр
    0.40
    Activations Density 0.001%

    No Known Activations