© 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. 52287
    Prev
    Next
    INDEX
    Explanations

    code processing wc and current

    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
    conditionals
    0.47
     Tyson
    0.47
     Telecom
    0.46
    brasil
    0.46
     industri
    0.45
     orifice
    0.45
    洩
    0.44
     inputValue
    0.44
     Nascimento
    0.43
     adsorption
    0.43
    POSITIVE LOGITS
    wend
    0.51
    0.46
     Союза
    0.44
     rekan
    0.43
     сов
    0.43
    čki
    0.43
    vrd
    0.42
    ciaux
    0.42
    vh
    0.41
     ston
    0.41
    Activations Density 0.005%

    No Known Activations