© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1800
    Prev
    Next
    INDEX
    Explanations

    G followed by specific word beginnings

    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
    期
    1.89
    idences
    1.55
     insign
    1.52
     gallium
    1.49
     compuls
    1.48
    cyon
    1.48
    رخ
    1.43
    תר
    1.42
    IELD
    1.42
    詫
    1.42
    POSITIVE LOGITS
    raphe
    2.39
    ümüş
    2.29
    reetings
    2.27
    raphene
    2.24
    redient
    2.20
    othic
    2.06
    redients
    2.06
    oliath
    2.06
    orithms
    2.00
    rieve
    1.98
    Activations Density 0.290%

    No Known Activations