© 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. 31-GEMMASCOPE-2-RES-262K
    7. 44156
    Prev
    Next
    INDEX
    Explanations

    describing properties of things

    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
     bonita
    0.46
    ന്നാ
    0.43
    iban
    0.42
     mauve
    0.42
     krijgt
    0.42
     பிச்சு
    0.42
     puff
    0.41
    码
    0.41
    뻤
    0.41
     deliveries
    0.41
    POSITIVE LOGITS
    0
    0.54
    ीय
    0.53
     Theorems
    0.49
    任意の
    0.48
    AM
    0.47
     प्रसि
    0.46
    アル
    0.44
    Write
    0.44
    けない
    0.44
    世界
    0.43
    Activations Density 0.002%

    No Known Activations