© 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. 200517
    Prev
    Next
    INDEX
    Explanations

    working hours, interest rates

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

    video folder structure

    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
    the
    0.49
    共和国
    0.46
    ﺩ
    0.46
     ؟
    0.44
     futur
    0.44
     در
    0.43
     کریں
    0.43
    ста
    0.43
    隆
    0.43
    in
    0.43
    POSITIVE LOGITS
     totaling
    0.46
     নিজেরাই
    0.44
     kellett
    0.43
     источ
    0.42
     automaticamente
    0.42
     finding
    0.42
    finding
    0.42
    ിക്കുകയും
    0.42
     averiguar
    0.42
     চেয়েছিলেন
    0.42
    Activations Density 0.000%

    No Known Activations