© 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. 31-GEMMASCOPE-2-RES-65K
    7. 51890
    Prev
    Next
    INDEX
    Explanations

    entity followed by state or action

    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_31_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
     tempus
    0.38
     provides
    0.38
     SWAT
    0.37
     такую
    0.37
     subsided
    0.35
     Σ
    0.35
     bureaucratic
    0.35
     subside
    0.35
     తీసుకు
    0.34
     comes
    0.34
    POSITIVE LOGITS
    및
    0.50
     एवं
    0.49
    /
    0.47
    और
    0.46
    andfeel
    0.44
     والم
    0.42
     आणि
    0.42
     மற்றும்
    0.42
    及
    0.41
     aau
    0.40
    Activations Density 0.133%

    No Known Activations