© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 727
    Prev
    Next
    INDEX
    Explanations

    double negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     caos
    0.35
    鹜
    0.35
    прочем
    0.35
    жать
    0.33
     observaciones
    0.33
     hablaremos
    0.33
    ocsát
    0.33
    panies
    0.33
    ᇂ
    0.32
    )。
    0.32
    POSITIVE LOGITS
     is
    0.44
     easy
    0.41
     durable
    0.40
     lightweight
    0.38
     was
    0.37
     reusable
    0.36
     sturdy
    0.36
     biodegradable
    0.35
     Durable
    0.35
     great
    0.35
    Activations Density 0.000%

    No Known Activations