© 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. 62556
    Prev
    Next
    INDEX
    Explanations

    public key concept

    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
    [
    0.55
    n
    0.46
    er
    0.45
     verstär
    0.42
     renforc
    0.42
     denuncia
    0.42
    an
    0.41
    oxo
    0.41
    }^{-}\
    0.40
     komplett
    0.39
    POSITIVE LOGITS
    מצע
    0.51
    ంద
    0.45
    আই
    0.45
     વિદ્ય
    0.45
     परमा
    0.44
    ఛ
    0.44
    IAM
    0.43
     ലോ
    0.43
     கட்டமை
    0.42
     પારિજા
    0.42
    Activations Density 0.020%

    No Known Activations