© 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. 48589
    Prev
    Next
    INDEX
    Explanations

    testing and comparing alternatives

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

    evaluating effectiveness, models, and candidates

    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
    wealth
    0.47
    ليل
    0.44
    颓
    0.43
    Diagnosis
    0.41
    requis
    0.39
    싫
    0.39
    ลิ
    0.39
    ક્ર
    0.39
     ఆల
    0.38
    ึ
    0.38
    POSITIVE LOGITS
     proposed
    0.75
     alternatives
    0.71
     tested
    0.70
     various
    0.69
     alternative
    0.69
     candidates
    0.67
     methods
    0.66
     strategies
    0.66
     Tested
    0.64
     newer
    0.64
    Activations Density 0.126%

    No Known Activations