© 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. 52603
    Prev
    Next
    INDEX
    Explanations

    describes qualities

    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
    мун
    0.40
    ikken
    0.39
    azepam
    0.39
     nevoia
    0.39
     احترام
    0.38
    𝒞
    0.38
    🅐
    0.38
    Estos
    0.38
     전망
    0.38
    িয়াম
    0.38
    POSITIVE LOGITS
     '$
    0.46
     outdoor
    0.46
     Outdoor
    0.46
     Lists
    0.45
     Laugh
    0.44
     Lawyer
    0.43
    outdoor
    0.42
     Fortune
    0.42
     Inline
    0.41
     Version
    0.41
    Activations Density 0.003%

    No Known Activations