© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 55873
    Prev
    Next
    INDEX
    Explanations

    TeX Live and TeXmaker software

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_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
    ıyor
    0.45
    ണിത്
    0.44
     alimenta
    0.44
    忝
    0.43
     ridicu
    0.43
    arzt
    0.42
     Shukla
    0.42
     OBJECTTYPE
    0.41
    𝟯
    0.41
    Parrocchia
    0.41
    POSITIVE LOGITS
     heavily
    0.44
     heavy
    0.38
     Jet
    0.38
     stack
    0.37
     custom
    0.37
     close
    0.36
    versions
    0.36
     cherry
    0.35
     extensive
    0.35
     hal
    0.35
    Activations Density 0.002%

    No Known Activations