© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17709
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and proofs

    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
    كة
    0.46
    تاة
    0.45
    :“
    0.44
     ইস্য
    0.44
    .“
    0.44
     refuse
    0.43
     माँ
    0.43
    💙
    0.43
     forem
    0.43
     ఇటీవల
    0.42
    POSITIVE LOGITS
     stochastic
    0.57
     spectroscopy
    0.56
     perturbed
    0.55
     perturbative
    0.53
     Galois
    0.53
     spectroscopic
    0.52
     trivially
    0.51
     Spectroscopy
    0.51
     topological
    0.51
    MathClass
    0.51
    Activations Density 0.003%

    No Known Activations