© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 4697
    Prev
    Next
    INDEX
    Explanations

    people and associates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     défini
    0.62
    늦
    0.59
     definida
    0.56
    കൊണ്ട്
    0.56
    }$=
    0.55
     definidas
    0.55
     Sélectionnez
    0.54
     definiert
    0.52
     eenvoudig
    0.52
    separator
    0.52
    POSITIVE LOGITS
     who
    0.84
     whom
    0.81
    𓃵
    0.79
     প্রমুখ
    0.73
    ’
    0.68
     وغير
    0.68
    等人
    0.68
     ಅವರ
    0.65
     himself
    0.65
     など
    0.64
    Activations Density 0.532%

    No Known Activations