© 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. 153215
    Prev
    Next
    INDEX
    Explanations

    She says

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

    organic whole, thrives, reduces

    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
    Negative Logits
     ହ
    0.49
    няў
    0.46
     éves
    0.45
     godinu
    0.44
     colonne
    0.44
     已
    0.43
     år
    0.42
     april
    0.42
     թվ
    0.41
     abril
    0.41
    POSITIVE LOGITS
    S
    0.47
    C
    0.47
     selfless
    0.46
     narcotic
    0.43
    X
    0.43
    T
    0.43
     ইস্যুতে
    0.42
     spoils
    0.42
     dispens
    0.41
     யோ
    0.41
    Activations Density 0.000%

    No Known Activations