© 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. 195691
    Prev
    Next
    INDEX
    Explanations

    in dependence on

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

    storylines development

    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
    ா
    0.49
    𝘬
    0.46
    ಾಯ
    0.45
    ון
    0.45
     junge
    0.45
     остров
    0.44
     সত্ত্বেও
    0.44
     சது
    0.43
    に応
    0.43
    瞭
    0.43
    POSITIVE LOGITS
    USDA
    0.43
    Blogs
    0.42
     Nutr
    0.41
    ikken
    0.40
    Noeud
    0.40
    땔
    0.40
    Oklahoma
    0.39
    BOOLE
    0.39
     basilaires
    0.39
     executes
    0.39
    Activations Density 0.002%

    No Known Activations