© 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. 16182
    Prev
    Next
    INDEX
    Explanations

    Kapitel, stücke, episode

    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
    Anonymous
    0.57
     itu
    0.49
    G
    0.48
     Kay
    0.46
    Anon
    0.46
    Kay
    0.45
     putra
    0.45
    ادو
    0.44
    どん
    0.44
     semoga
    0.44
    POSITIVE LOGITS
     Kapitel
    0.45
    stücke
    0.44
     Episode
    0.44
     anecdote
    0.43
     õ
    0.43
    kurs
    0.42
    kopf
    0.42
    nessy
    0.41
    rollen
    0.41
    stellt
    0.41
    Activations Density 0.005%

    No Known Activations