© 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. 54275
    Prev
    Next
    INDEX
    Explanations

    calculating sums and lists

    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
     tetahi
    0.44
    埗
    0.44
    prompt
    0.43
    see
    0.42
    udarstven
    0.40
    îtier
    0.40
    and
    0.39
    avond
    0.39
    i
    0.39
    uangan
    0.38
    POSITIVE LOGITS
     hypothesis
    0.48
     عَ
    0.47
     intron
    0.43
    ENUM
    0.42
     hypothesize
    0.42
     ह
    0.42
     decipher
    0.42
     ս
    0.42
     mathematician
    0.42
    灝
    0.41
    Activations Density 0.071%

    No Known Activations