© 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. 195363
    Prev
    Next
    INDEX
    Explanations

    adverb + adjective/noun

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

    Folate, begun, growing, copy, limited, anything

    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
    ده
    0.42
     ছিলাম
    0.41
    ？
    0.39
     MOS
    0.39
    （
    0.39
    ؟
    0.39
    или
    0.39
    ﻂ
    0.39
    Sierra
    0.38
    ",
    0.38
    POSITIVE LOGITS
     Nachdem
    0.49
    }.}
    0.48
     말씀을
    0.47
    ্বরের
    0.45
    .`);
    0.45
     Enseñ
    0.44
     በማ
    0.44
    }^{*}=\
    0.44
     앞에서
    0.44
     ఇప్పటికే
    0.44
    Activations Density 0.000%

    No Known Activations