© 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
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15636
    Prev
    Next
    INDEX
    Explanations

    actions or states followed by context

    np_acts-logits-general · gemini-2.5-flash-lite

    height or size adjectives

    np_acts-logits-general · gemini-2.5-flash-lite

    instructional procedures

    np_max-act-logits · claude-4-5-sonnetTriggered by @sk5695
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    0.63
    -
    0.57
    ،
    0.42
     iteratively
    0.42
     কিংবা
    0.42
    ，
    0.42
     in
    0.41
    ,...,
    0.41
     doctoral
    0.41
    、
    0.40
    POSITIVE LOGITS
    ੧
    0.51
    descricao
    0.50
    porque
    0.48
    אי
    0.47
    acidade
    0.46
     protože
    0.46
    ܡܪ
    0.46
    伨
    0.46
    เพราะ
    0.44
    accion
    0.44
    Activations Density 0.111%

    No Known Activations