© 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. 51989
    Prev
    Next
    INDEX
    Explanations

    Standard Model description

    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
    mass
    0.45
     mass
    0.43
    entgen
    0.38
    ektor
    0.37
     masa
    0.36
    ಳ್ಳಿ
    0.36
    dbg
    0.36
    額
    0.36
    ardt
    0.36
    AVY
    0.35
    POSITIVE LOGITS
     Standard
    0.47
     incongru
    0.46
     forces
    0.46
     стандарт
    0.46
     Chrome
    0.44
     standart
    0.43
     עי
    0.42
     description
    0.41
    鸫
    0.41
     Description
    0.41
    Activations Density 0.029%

    No Known Activations