© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 9316
    Prev
    Next
    INDEX
    Explanations

    question about something new

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nel
    1.38
    el
    1.27
    นิยม
    1.26
    le
    1.23
    ో
    1.20
    am
    1.18
    స్సు
    1.17
    nelles
    1.16
    t
    1.15
    lı
    1.14
    POSITIVE LOGITS
    REDIRECT
    1.26
    Whats
    1.26
     unleashing
    1.25
     Army
    1.18
     Sys
    1.18
     conco
    1.15
    辕
    1.15
    امج
    1.14
    entially
    1.13
     grounds
    1.13
    Activations Density 0.000%

    No Known Activations