© 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. 46396
    Prev
    Next
    INDEX
    Explanations

    detailed descriptions

    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
    atthena
    0.42
     tehát
    0.41
    Фран
    0.40
    Bonjour
    0.38
    York
    0.37
    а
    0.35
    ̉a
    0.35
    acic
    0.35
    ）,
    0.35
     фильм
    0.35
    POSITIVE LOGITS
     decisiones
    0.49
     solns
    0.48
     partying
    0.45
     కీలక
    0.45
     boundaries
    0.45
    咋
    0.45
    ഞ്ഞു
    0.44
     Desenvolvimento
    0.44
     పరిష్
    0.44
     EVERYTHING
    0.44
    Activations Density 0.038%

    No Known Activations