© 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. 3185
    Prev
    Next
    INDEX
    Explanations

    random number generation

    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
     Navigate
    2.19
     Simplify
    2.18
     Glor
    2.16
    𝙮
    2.14
    善
    2.07
    orchid
    2.05
    েম
    2.01
     பெற
    1.96
    NOP
    1.96
    িদ্ধ
    1.95
    POSITIVE LOGITS
    tan
    2.25
    shank
    2.14
    tf
    2.11
    tl
    2.11
    lymp
    2.03
    manes
    1.99
    lywood
    1.98
    nden
    1.98
    ल्लाह
    1.98
    `${
    1.96
    Activations Density 0.045%

    No Known Activations