© 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. 138794
    Prev
    Next
    INDEX
    Explanations

    Prior to or goals to

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

    beneficial, limited, important, basic

    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
    춘
    0.48
     A
    0.47
    ้
    0.46
    려
    0.46
    달
    0.45
    자
    0.44
     Poverty
    0.43
    한
    0.43
    近
    0.43
    ಳ
    0.42
    POSITIVE LOGITS
    
    0.47
    BagConstraints
    0.45
     played
    0.44
    prits
    0.44
     faintly
    0.44
    रोप
    0.43
    ப்பது
    0.42
    läufig
    0.42
    áneamente
    0.42
    anlage
    0.41
    Activations Density 0.001%

    No Known Activations