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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 12637
    Prev
    Next
    INDEX
    Explanations

    terms of endearment

    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_65k_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
     worse
    0.49
    ಕ್ಕಿಂತ
    0.45
     quarterfinals
    0.45
     horribly
    0.42
     gratis
    0.41
     ironically
    0.40
    urably
    0.40
    ()`
    0.40
    कविता
    0.39
    outheast
    0.39
    POSITIVE LOGITS
    策
    0.44
     adventurer
    0.43
    PictureBox
    0.39
    சார
    0.38
    Formatter
    0.37
    шень
    0.37
    രി
    0.37
    रे
    0.37
    ге
    0.37
    යා
    0.37
    Activations Density 0.060%

    No Known Activations