© 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. 96486
    Prev
    Next
    INDEX
    Explanations

    move operations fertility before get go

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

    Here's a detailed

    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
     أكبر
    0.47
     μεγαλύτε
    0.45
     棉
    0.43
     ঢেউ
    0.43
     جمهور
    0.41
     حجم
    0.41
     發
    0.40
     होमवर्क
    0.40
     Ángeles
    0.40
     मौजूदगी
    0.40
    POSITIVE LOGITS
    厩
    0.49
    ꯋ
    0.49
    cL
    0.47
    bserv
    0.46
     urma
    0.45
    ລ
    0.45
    
    0.44
    िलासपुर
    0.44
     restricts
    0.44
    ghe
    0.44
    Activations Density 0.000%

    No Known Activations