© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3379
    Prev
    Next
    INDEX
    Explanations

    past actions or states

    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_7_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
    ামুটি
    2.74
    बल
    2.50
    ivative
    2.36
    𝘩
    2.25
    ่ว
    2.22
    curities
    2.20
    żeń
    2.15
    인을
    2.07
    isyen
    2.06
    力的
    2.05
    POSITIVE LOGITS
    ే
    3.10
    es
    3.08
    ের
    2.99
    s
    2.96
    ে
    2.94
    ร้อง
    2.89
    ي
    2.79
    en
    2.77
    ो
    2.74
    𝙚
    2.74
    Activations Density 0.119%

    No Known Activations