© 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. 16-GEMMASCOPE-2-RES-262K
    7. 16974
    Prev
    Next
    INDEX
    Explanations

    important notes before

    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_16_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
    -
    0.46
    UN
    0.41
    、
    0.40
    /
    0.39
    HR
    0.37
    ፣
    0.37
    ISA
    0.36
    IM
    0.36
    हरु
    0.36
    _
    0.36
    POSITIVE LOGITS
     invariant
    0.40
     idempotent
    0.39
     flanking
    0.38
     DeConcini
    0.38
    ！)
    0.38
     Lévy
    0.37
    Radiux
    0.37
     dàng
    0.37
     Colombeau
    0.36
     beak
    0.36
    Activations Density 0.183%

    No Known Activations