© 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. 202088
    Prev
    Next
    INDEX
    Explanations

    expert opined, this chapter, blogging

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

    london contact

    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
     도시
    0.49
     ビ
    0.49
     मिलीमीटर
    0.47
     어린
    0.46
    ି
    0.46
     Cidade
    0.45
    炸
    0.44
    ^{\
    0.44
     الخام
    0.44
     Akk
    0.44
    POSITIVE LOGITS
    ඖ
    0.50
     innovación
    0.46
    Rahul
    0.45
     doctora
    0.45
    intuitive
    0.44
    katapos
    0.43
    ጂ
    0.42
    ྨ
    0.41
    हरू
    0.41
     භාවිත
    0.40
    Activations Density 0.000%

    No Known Activations