© 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. 233594
    Prev
    Next
    INDEX
    Explanations

    mind is, remember is

    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
    call
    0.45
     Đo
    0.42
    I
    0.42
     op
    0.42
    failure
    0.42
     erw
    0.41
    r
    0.41
     declarations
    0.40
     ajud
    0.40
    render
    0.40
    POSITIVE LOGITS
     стрельца
    0.62
     연구
    0.56
     움
    0.54
     카
    0.54
     시민
    0.52
     포
    0.52
     희
    0.52
     몇
    0.51
     메
    0.50
    한
    0.50
    Activations Density 0.000%

    No Known Activations