© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 112927
    Prev
    Next
    INDEX
    Explanations

    scent of lavender

    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_262k_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
    il
    0.49
    i
    0.45
    targeting
    0.43
    initial
    0.43
    u
    0.43
    iencia
    0.42
    arq
    0.42
    er
    0.42
    im
    0.42
    jmath
    0.42
    POSITIVE LOGITS
    სი
    0.47
    〠
    0.44
     tertinggi
    0.43
     nextline
    0.43
     konfl
    0.43
    ಷ್ಣ
    0.42
     flexibly
    0.42
    SI
    0.41
    קור
    0.41
    虚拟机
    0.41
    Activations Density 0.002%

    No Known Activations