© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 993
    Prev
    Next
    INDEX
    Explanations

    2. stigmata

    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
    ினார்
    2.17
    <bos>
    2.08
    se
    2.06
    comend
    1.97
    encion
    1.96
    zor
    1.89
    ش
    1.88
    ział
    1.86
    ‌
    1.85
     pokok
    1.84
    POSITIVE LOGITS
    nd
    3.33
    ﮈ
    2.95
    nds
    2.69
    ﻟ
    2.64
    ними
    2.52
    स्ताना
    2.52
    ﺑ
    2.51
    ное
    2.49
    нима
    2.46
    𝗻
    2.46
    Activations Density 1.187%

    No Known Activations