© 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. 54820
    Prev
    Next
    INDEX
    Explanations

    agreement and terms

    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
     basura
    0.47
    乐观
    0.46
    ου
    0.45
    ༔
    0.45
    ер
    0.45
    ノン
    0.44
     siento
    0.43
     suelos
    0.43
     আসিল
    0.43
    ˬ
    0.43
    POSITIVE LOGITS
    al
    0.55
    ce
    0.52
    it
    0.51
    itre
    0.51
    ice
    0.50
    in
    0.48
    ire
    0.47
     Al
    0.46
    d
    0.46
    ast
    0.44
    Activations Density 0.005%

    No Known Activations