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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    whispered stories secrets conversation

    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
    <bos>
    2.39
    جاج
    2.16
    ت
    2.16
    tır
    2.14
     حاض
    2.13
     tim
    2.12
    拶
    2.07
    太
    2.07
    ्ञ
    2.06
    ダル
    2.06
    POSITIVE LOGITS
    ριθ
    2.23
    res
    2.16
    𝗳
    2.14
    𝘇
    2.10
    cat
    2.04
    bbb
    2.00
    REE
    1.99
    factors
    1.99
    reth
    1.99
     successors
    1.99
    Activations Density 0.028%

    No Known Activations