© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 3560
    Prev
    Next
    INDEX
    Explanations

    BIOS and motherboards

    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
    BLACKLIST
    2.51
    ical
    2.49
    anak
    2.46
    ྥ
    2.43
    лава
    2.42
    alities
    2.41
     忄
    2.33
    лъ
    2.33
    Famous
    2.31
    োভ
    2.31
    POSITIVE LOGITS
     segi
    2.39
    ்துறை
    2.32
    खिक
    2.27
    팅
    2.25
    $/../../../../
    2.19
    хом
    2.17
    हिणी
    2.15
    য়া
    2.14
     按
    2.13
    حة
    2.11
    Activations Density 0.039%

    No Known Activations