© 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. 84133
    Prev
    Next
    INDEX
    Explanations

    This must include

    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
    แต่ละ
    0.47
    粦
    0.44
    𝘪
    0.44
    रण
    0.43
    жах
    0.43
    让他们
    0.43
     अभिनय
    0.43
    რის
    0.42
    寯
    0.42
    рованы
    0.41
    POSITIVE LOGITS
     ammonium
    0.52
     salts
    0.49
     countries
    0.47
     developers
    0.47
     change
    0.46
     chloride
    0.45
     end
    0.44
     fresh
    0.44
     troops
    0.44
     south
    0.43
    Activations Density 0.004%

    No Known Activations