© 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. 28068
    Prev
    Next
    INDEX
    Explanations

    monetary net worth

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

    frustrated or swallow

    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
     주요
    0.51
     Paradise
    0.48
     Banking
    0.46
     शुक्रवार
    0.44
    Paradise
    0.43
    ऑ
    0.43
     Maiden
    0.42
    たっぷ
    0.41
    🌴
    0.41
     प्रतिनि
    0.40
    POSITIVE LOGITS
     overkill
    0.55
     anderes
    0.53
     verlieren
    0.45
     consequ
    0.44
    esquerdo
    0.44
    etition
    0.44
     неуда
    0.44
    TGFuZ
    0.43
    anatom
    0.43
    其他的
    0.42
    Activations Density 0.000%

    No Known Activations