© 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. 12487
    Prev
    Next
    INDEX
    Explanations

    categorizing by complexity or level

    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
    neq
    0.46
    ভিড
    0.44
    nel
    0.38
    ftime
    0.38
    imą
    0.38
     jīn
    0.37
     భ
    0.37
     વૃ
    0.37
    Album
    0.37
    nout
    0.36
    POSITIVE LOGITS
     levels
    1.20
     level
    1.15
     niveles
    1.03
    ระดับ
    1.02
     livelli
    1.02
     níveis
    1.02
     niveau
    1.01
    levels
    1.01
    レベル
    1.01
    Level
    0.98
    Activations Density 0.615%

    No Known Activations