© 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. 40-GEMMASCOPE-2-RES-65K
    7. 53669
    Prev
    Next
    INDEX
    Explanations

    understand, store, file, boxes, position, shutdown

    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
     totalled
    0.39
     англий
    0.39
    [\
    0.38
    日本語
    0.38
     назна
    0.37
     ಹಣ
    0.37
    umbr
    0.37
    ':
    0.37
     centred
    0.36
     तों
    0.36
    POSITIVE LOGITS
     underestimate
    0.37
     Paese
    0.37
    圣诞
    0.36
     frans
    0.36
     Chamber
    0.36
     below
    0.36
     chamber
    0.36
    Methylsulfanyl
    0.36
    ர்க்க
    0.36
    below
    0.36
    Activations Density 0.000%

    No Known Activations