© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 54301
    Prev
    Next
    INDEX
    Explanations

    collection planning

    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
     महिला
    0.49
    raš
    0.45
    érard
    0.44
     мо
    0.44
     모
    0.44
    रा
    0.43
     초
    0.43
    𐰀
    0.43
     красно
    0.42
     농
    0.41
    POSITIVE LOGITS
     internationaux
    0.46
     sulfides
    0.43
     albums
    0.42
     religions
    0.42
     independents
    0.42
     ambitions
    0.41
     স্বীকৃতি
    0.41
     intérêts
    0.40
     Albums
    0.40
     superconductors
    0.39
    Activations Density 0.021%

    No Known Activations