© 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-262K
    7. 201126
    Prev
    Next
    INDEX
    Explanations

    cos θ

    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
    并且
    0.42
    Corporate
    0.41
    Vendor
    0.40
     Conceptual
    0.40
    Conceptual
    0.40
    पो
    0.39
    着
    0.39
    O
    0.39
     ներ
    0.39
    이며
    0.38
    POSITIVE LOGITS
     auraient
    0.52
    returnValue
    0.48
     aurait
    0.47
     bolster
    0.46
     niece
    0.46
     untenable
    0.46
     negligent
    0.45
     basaltes
    0.45
    there
    0.45
     jealous
    0.45
    Activations Density 0.006%

    No Known Activations