© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132854
    Prev
    Next
    INDEX
    Explanations

    apply a service

    np_acts-logits-general · gemini-2.5-flash-lite

    markdown structure or formatting characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    toj
    0.49
     atividade
    0.47
     مبس
    0.46
     (+)
    0.46
    oyle
    0.45
    teddy
    0.45
    jari
    0.44
    them
    0.44
     nullable
    0.43
     মজুম
    0.43
    POSITIVE LOGITS
    Ņ
    0.49
    録
    0.46
    Ờ
    0.46
    건
    0.46
    광
    0.45
    ନ
    0.45
    긴
    0.45
    층
    0.45
    ണാ
    0.44
     Leno
    0.44
    Activations Density 0.001%

    No Known Activations