© 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. 66977
    Prev
    Next
    INDEX
    Explanations

    anchoring members

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

    Hamilton, Texas, State, just, rinsing

    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
    f
    0.60
    st
    0.59
    ting
    0.57
    ically
    0.55
    x
    0.53
    bent
    0.52
    max
    0.51
    ient
    0.51
    kring
    0.49
    controller
    0.49
    POSITIVE LOGITS
     visok
    0.53
     THEM
    0.50
     vasculaire
    0.50
    ክምና
    0.48
    ብዙ
    0.48
    ᱪ
    0.47
    劭
    0.46
     labai
    0.46
     konkuren
    0.46
     ficción
    0.46
    Activations Density 0.000%

    No Known Activations