© 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. 37699
    Prev
    Next
    INDEX
    Explanations

    understand, porque, the

    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
     было
    0.50
     помі
    0.49
    猟
    0.49
     ကု
    0.46
    行った
    0.46
     исследование
    0.46
    ִי
    0.45
    ά
    0.45
    性を
    0.45
    μα
    0.45
    POSITIVE LOGITS
    Tw
    0.59
    Lo
    0.48
    GSM
    0.47
    Quick
    0.46
    hl
    0.46
    Sp
    0.45
    Fun
    0.45
    Pet
    0.45
    fun
    0.44
    _)
    0.44
    Activations Density 0.000%

    No Known Activations