© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92162
    Prev
    Next
    INDEX
    Explanations

    invadopodia cores, king's paths, Christ, classes

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

    religious fanaticism or death

    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
    y
    0.64
    t
    0.55
    p
    0.54
     พิจ
    0.50
    T
    0.50
    lin
    0.49
    𝑇
    0.47
     cose
    0.47
     matchups
    0.47
    yCoordinate
    0.46
    POSITIVE LOGITS
     câu
    0.51
     papier
    0.45
     Diner
    0.44
    шению
    0.42
    ชีพ
    0.42
    |^{\
    0.41
    ॉक
    0.40
    imento
    0.40
     ugy
    0.40
     نوم
    0.40
    Activations Density 0.000%

    No Known Activations