© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 7713
    Prev
    Next
    INDEX
    Explanations

    foundations or underlying structures

    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
    ened
    0.51
    ம்
    0.47
     nei
    0.45
     intér
    0.45
     PLE
    0.45
     LDGs
    0.45
    م
    0.45
    umbled
    0.45
    anticipated
    0.44
     fora
    0.44
    POSITIVE LOGITS
     blanchâtre
    0.50
     cockro
    0.45
     Beratung
    0.45
     Lebens
    0.45
     дошко
    0.44
     renovating
    0.44
     дія
    0.43
     Carta
    0.43
     التربيع
    0.43
    𒆜
    0.43
    Activations Density 0.003%

    No Known Activations