© 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-262K
    7. 213002
    Prev
    Next
    INDEX
    Explanations

    (* species name *):**

    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_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
     тел
    0.43
    elevationMap
    0.43
     нынеш
    0.42
    ቷ
    0.42
     नव
    0.42
    icht
    0.40
    ěn
    0.40
    ève
    0.40
    atts
    0.39
    ählte
    0.39
    POSITIVE LOGITS
     जोड़
    0.41
    ಂಟ
    0.39
     Puro
    0.37
    ObjectModel
    0.37
    ⁡
    0.37
     Unt
    0.36
    ̾
    0.36
     Ult
    0.36
    আন্ত
    0.35
    ㊙
    0.35
    Activations Density 0.000%

    No Known Activations