© 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. 73804
    Prev
    Next
    INDEX
    Explanations

    never fall

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

    explaining why or how

    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
     Silicon
    0.46
     maine
    0.46
     MR
    0.46
     Radiological
    0.46
     stunt
    0.46
    </h3>
    0.45
     protest
    0.45
     Neon
    0.44
     hoop
    0.44
     california
    0.44
    POSITIVE LOGITS
    ٥
    0.59
    expect
    0.57
    on
    0.57
    ೫
    0.56
    as
    0.53
    ان
    0.51
    un
    0.50
    an
    0.49
    all
    0.49
    ۵
    0.49
    Activations Density 0.000%

    No Known Activations