© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90573
    Prev
    Next
    INDEX
    Explanations

    presenting choices for

    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_31_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
    art
    0.59
    ad
    0.52
    ل
    0.49
    att
    0.48
    اح
    0.46
    endem
    0.46
    ق
    0.46
    typography
    0.45
    emas
    0.45
    adia
    0.45
    POSITIVE LOGITS
    ~)
    0.45
     ໜອງ
    0.45
    '])]
    0.45
    ()))
    0.45
    *',
    0.45
    ]][
    0.44
    馕
    0.44
    ！」
    0.44
    ))]
    0.44
    -]
    0.43
    Activations Density 0.001%

    No Known Activations