© 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. 11130
    Prev
    Next
    INDEX
    Explanations

    Linux command-line instructions

    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
    鹉
    3.02
    ान
    2.85
    之为
    2.76
    <unused1139>
    2.74
    anın
    2.72
     WF
    2.70
    ︎
    2.69
     pretensions
    2.64
    󠁬
    2.61
     karit
    2.61
    POSITIVE LOGITS
    voll
    2.57
    o
    2.42
    ಿಂದ
    2.33
    м
    2.29
    eppo
    2.28
     ভো
    2.23
    ו
    2.14
    zés
    2.13
    varande
    2.13
    oost
    2.10
    Activations Density 0.030%

    No Known Activations