© 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-65K
    7. 29621
    Prev
    Next
    INDEX
    Explanations

    learning and conventional

    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
     pirate
    0.33
     a
    0.33
     pirates
    0.32
     Wetlands
    0.32
     Pyramid
    0.32
     backstage
    0.32
     Bored
    0.31
     nærm
    0.31
     boredom
    0.31
    ?
    0.31
    POSITIVE LOGITS
     conventional
    0.44
    conventional
    0.44
    通常の
    0.43
    Conventional
    0.42
     சாதாரண
    0.40
    普通の
    0.39
     Conventional
    0.38
     Alongside
    0.36
    Alongside
    0.35
     পাশাপাশি
    0.35
    Activations Density 0.862%

    No Known Activations