© 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. 40-GEMMASCOPE-2-RES-65K
    7. 55919
    Prev
    Next
    INDEX
    Explanations

    Vampire, Vampiric, Vampire Survivors

    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_40_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
     estratégico
    0.43
     ನಡುವ
    0.43
     feeder
    0.42
    )[
    0.40
     fato
    0.40
    broke
    0.39
    🍖
    0.39
     похађа
    0.39
    navigationLinks
    0.38
     crockery
    0.38
    POSITIVE LOGITS
    OMET
    0.46
    Interface
    0.44
    ILLA
    0.41
     Part
    0.41
    y
    0.41
    part
    0.40
    system
    0.39
     Robot
    0.39
     Supreme
    0.39
    Labor
    0.39
    Activations Density 0.004%

    No Known Activations