© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1914
    Prev
    Next
    INDEX
    Explanations

    technical SEO, theory, hoarding disorder, Lore, autophagy, Play

    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_16k_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
    en
    1.51
    asambhavam
    1.38
    ಷ್ಠ
    1.36
    ಾ
    1.36
    नून
    1.34
     voila
    1.31
    Segoe
    1.25
    currentToken
    1.25
    ರ
    1.25
    ৈতিক
    1.24
    POSITIVE LOGITS
    のが
    1.36
    osse
    1.32
     које
    1.28
    ச்
    1.22
     corral
    1.21
    ه
    1.20
     massive
    1.20
    oss
    1.19
    হ
    1.19
     identical
    1.16
    Activations Density 0.034%

    No Known Activations