© 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-16K
    7. 3910
    Prev
    Next
    INDEX
    Explanations

    fetching data with GET

    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_16k_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
     வகைகள்
    0.45
    嗯
    0.43
    Fonte
    0.43
     অপারেটিং
    0.43
    போதும்
    0.43
     തല
    0.43
     äuß
    0.43
    உங்கள்
    0.41
    ArgsEnv
    0.41
    📐
    0.41
    POSITIVE LOGITS
     fetch
    0.43
     trin
    0.43
     acupuncture
    0.42
     decou
    0.42
     telehealth
    0.41
     single
    0.40
     custom
    0.40
     conditional
    0.40
     Bayesian
    0.40
     multivariate
    0.40
    Activations Density 0.262%

    No Known Activations