© 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. 6723
    Prev
    Next
    INDEX
    Explanations

    identifying variables in formulas

    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
    できなかった
    0.41
    ា
    0.40
    the
    0.39
    ്യാപ
    0.39
     hexadecimal
    0.39
     Markdown
    0.37
    ля
    0.37
    タ
    0.37
     skew
    0.36
     সুইড
    0.36
    POSITIVE LOGITS
     இருக்கிறது
    0.44
     दृष्टि
    0.43
    λύ
    0.43
     fidèle
    0.42
    兕
    0.41
    λογή
    0.41
    ✱
    0.40
    etically
    0.40
    侶
    0.39
     aberta
    0.39
    Activations Density 0.020%

    No Known Activations