© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 526
    Prev
    Next
    INDEX
    Explanations

    diverse languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_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
    endswith
    0.69
    fila
    0.68
     část
    0.59
    VB
    0.58
    gb
    0.57
    Gert
    0.56
    barn
    0.54
    叩
    0.54
    TWI
    0.50
    ストレ
    0.50
    POSITIVE LOGITS
    aceus
    1.45
    webElementGuid
    1.41
    слары
    1.40
    앵
    1.39
    дания
    1.37
    мести
    1.36
    了出来
    1.35
     ullamcorper
    1.35
     aurez
    1.33
    stylesheet
    1.32
    Activations Density 0.148%

    No Known Activations