© 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. 13635
    Prev
    Next
    INDEX
    Explanations

    generating requested content

    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
    ätta
    1.43
    <bos>
    1.32
    atts
    1.27
     sä
    1.18
    ʏ
    1.13
     rough
    1.11
    ็บ
    1.11
     tet
    1.10
    nimmt
    1.08
     Bet
    1.07
    POSITIVE LOGITS
    IONAL
    1.53
     мозга
    1.43
    Unsupported
    1.43
    짜
    1.40
    egos
    1.40
    वानिव
    1.39
     Childhood
    1.36
    eu
    1.35
     Imperio
    1.35
     Adoles
    1.35
    Activations Density 0.135%

    No Known Activations