© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135788
    Prev
    Next
    INDEX
    Explanations

    sequences of messages

    np_acts-logits-general · gemini-2.5-flash-lite

    following paths or instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    trunc
    0.59
    의
    0.53
    nya
    0.51
    up
    0.50
    껐
    0.50
    us
    0.49
    red
    0.49
    uttab
    0.48
    ن
    0.48
    enta
    0.47
    POSITIVE LOGITS
     szolgált
    0.48
     MIND
    0.45
     EBS
    0.44
    伦敦
    0.44
     hozz
    0.44
    遐
    0.44
     HTTPS
    0.43
     considerate
    0.43
     gitt
    0.43
     EHR
    0.42
    Activations Density 0.001%

    No Known Activations