© 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. 1295
    Prev
    Next
    INDEX
    Explanations

    skill levels

    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
    কেট
    2.44
     имущества
    2.30
     morbidity
    2.27
    vre
    2.17
     sanctioned
    2.13
     образа
    2.06
    н
    2.01
    docx
    2.01
    ￫
    2.00
     TOC
    1.98
    POSITIVE LOGITS
     essi
    2.45
     acumen
    2.27
     ausgestattet
    2.25
     zdol
    2.15
     persone
    2.13
    JSONArray
    2.12
     foresight
    2.10
    バイル
    2.06
    ial
    2.06
    ச
    2.05
    Activations Density 1.235%

    No Known Activations