© 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. 61833
    Prev
    Next
    INDEX
    Explanations

    detective investigating, emojis

    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
    🐿
    0.50
     религи
    0.49
     ponieważ
    0.47
    acije
    0.47
    aciju
    0.46
     ಉತ್ಪನ್ನ
    0.45
    査
    0.45
    kod
    0.44
    Inode
    0.43
    arlos
    0.43
    POSITIVE LOGITS
     immédi
    0.44
     Neptune
    0.44
     Techn
    0.44
     Magistrates
    0.44
     candle
    0.42
     début
    0.41
     pò
    0.41
    université
    0.39
    ୬
    0.39
    university
    0.39
    Activations Density 0.010%

    No Known Activations