© 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-16K
    7. 10899
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and symbols

    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
     correction
    0.39
    Â
    0.39
    False
    0.38
     nodig
    0.38
     dull
    0.38
    \(
    0.38
    oretical
    0.37
     preventing
    0.37
     chiar
    0.36
     evitare
    0.36
    POSITIVE LOGITS
    equivalent
    0.49
     anlamına
    0.47
    ]=="
    0.46
    相当于
    0.45
    ILIO
    0.45
    means
    0.44
    这件事
    0.44
    dollars
    0.44
    语言
    0.43
    literally
    0.42
    Activations Density 0.319%

    No Known Activations