Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3008
    Prev
    Next
    INDEX
    Explanations

    json and you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    렵
    1.30
    ੱਸ
    1.29
     susah
    1.27
     극
    1.27
     және
    1.27
    ционные
    1.26
     توصیه
    1.25
    kaç
    1.25
     һәм
    1.22
    ยาก
    1.22
    POSITIVE LOGITS
    ात्
    1.17
    —
    1.16
     revive
    1.16
     Connect
    1.08
     rehears
    1.07
     belonging
    1.07
     anim
    1.06
     Tissue
    1.06
     endors
    1.06
    :
    1.05
    Activations Density 0.001%

    No Known Activations