© 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. 62942
    Prev
    Next
    INDEX
    Explanations

    understand prompts

    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
     and
    0.37
     và
    0.37
    และ
    0.37
     आणि
    0.33
     ਅਤੇ
    0.33
    ส
    0.33
     W
    0.32
     और
    0.32
     ಮತ್ತು
    0.32
     is
    0.31
    POSITIVE LOGITS
     поведение
    0.36
    曈
    0.36
     vattum
    0.35
    鐟
    0.33
    <unused284>
    0.33
     podían
    0.33
     રાશિફળ
    0.33
     Verhalten
    0.32
     όταν
    0.32
     услы
    0.32
    Activations Density 0.001%

    No Known Activations