© 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-16K
    7. 5864
    Prev
    Next
    INDEX
    Explanations

    navigation, data, code

    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_16k_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
     dajj
    0.46
    ז
    0.43
    ﾓ
    0.43
     दैट
    0.42
    ント
    0.42
     および
    0.41
     prostagland
    0.41
    װ
    0.40
     역할
    0.40
     ಸಮಯದಲ್ಲಿ
    0.39
    POSITIVE LOGITS
     …
    0.67
     ·
    0.59
     ….
    0.57
     View
    0.52
    3
    0.47
    5
    0.47
     ...
    0.46
    ].
    0.46
     [];
    0.46
     […]
    0.45
    Activations Density 0.101%

    No Known Activations