© 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. 98874
    Prev
    Next
    INDEX
    Explanations

    terms, conditions, rights, clause

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

    rainbow blended, several blades, emotional neglect

    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
     institu
    0.46
    पु
    0.45
    予以
    0.45
    quantitative
    0.43
    i
    0.42
     commerciali
    0.42
    s
    0.40
     definitiva
    0.40
     Defin
    0.40
    erc
    0.39
    POSITIVE LOGITS
     باشید
    0.55
     बजरंग
    0.48
     የማይ
    0.47
    NeedConnect
    0.47
     ລ
    0.47
     ක්
    0.47
     शहनाज
    0.46
     کدام
    0.46
     부산
    0.46
     тебя
    0.46
    Activations Density 0.000%

    No Known Activations