© 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. 4653
    Prev
    Next
    INDEX
    Explanations

    usage and quantity management

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

    amounts and servings

    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
    political
    0.46
    ОВА
    0.44
     انف
    0.43
    АН
    0.40
     அரசியல்
    0.40
     बौद्ध
    0.40
    ИН
    0.39
    ང
    0.39
    ๙
    0.39
    짖
    0.39
    POSITIVE LOGITS
     refills
    0.87
     refill
    0.80
     servings
    0.71
     consumo
    0.69
     qty
    0.63
     deplete
    0.62
     consumption
    0.61
     مصرف
    0.61
    消耗
    0.61
     replenish
    0.61
    Activations Density 0.233%

    No Known Activations