© 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. 15453
    Prev
    Next
    INDEX
    Explanations

    in immediate or situational context

    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
     </
    0.38
     sharpen
    0.37
     stylized
    0.37
    glEnd
    0.36
     refreshments
    0.36
     Gandhiji
    0.36
     Mu
    0.35
     naar
    0.35
    pués
    0.35
    ↵
    0.35
    POSITIVE LOGITS
     posição
    0.61
     অবস্থানে
    0.57
     position
    0.55
     θέση
    0.55
     ситуация
    0.53
     Position
    0.52
    position
    0.52
    狀況
    0.52
     contention
    0.52
     posición
    0.51
    Activations Density 0.060%

    No Known Activations