© 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. 40-GEMMASCOPE-2-RES-262K
    7. 164728
    Prev
    Next
    INDEX
    Explanations

    funding flowed

    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
    ských
    0.39
     অবকাশ
    0.39
    加快
    0.38
    bollah
    0.37
    ята
    0.37
    ским
    0.36
    ᅣ
    0.35
    ياه
    0.35
    Ь
    0.35
    рано
    0.35
    POSITIVE LOGITS
     magnifier
    0.45
     birinci
    0.41
     peanut
    0.40
     reacting
    0.39
     Reflex
    0.39
     Peanut
    0.39
     muscle
    0.39
     difesa
    0.39
     martingale
    0.38
     splice
    0.38
    Activations Density 0.000%

    No Known Activations