© 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. 30968
    Prev
    Next
    INDEX
    Explanations

    have opportunity / annual revenue

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

    form stronger opinions

    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
     airline
    0.45
     milhões
    0.42
     legs
    0.41
    গত
    0.41
    '}$
    0.41
     Levine
    0.40
    َ
    0.39
    ेटिव
    0.39
    டிப்ப
    0.39
    อน
    0.38
    POSITIVE LOGITS
    ණු
    0.50
     エネルギー
    0.48
    rogram
    0.47
    eal
    0.47
    icuous
    0.47
     図
    0.47
     Tho
    0.45
    wirkung
    0.45
    hf
    0.45
     Vf
    0.45
    Activations Density 0.000%

    No Known Activations