© 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. 27501
    Prev
    Next
    INDEX
    Explanations

    A/B, single, couple, Law, computer, console

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

    heat or warmer years

    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
    Colorado
    0.46
    富
    0.45
    Farmers
    0.43
    Argent
    0.43
    の方は
    0.42
     آبی
    0.42
     पाउ
    0.42
    POL
    0.41
     တစ်
    0.41
     бога
    0.41
    POSITIVE LOGITS
     altid
    0.47
    r
    0.47
     ilyen
    0.46
     pozosta
    0.45
    .);
    0.43
     uvijek
    0.42
     odm
    0.41
     unfavourable
    0.41
    ...");
    0.41
     always
    0.41
    Activations Density 0.000%

    No Known Activations