© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 27269
    Prev
    Next
    INDEX
    Explanations

    is a / is the

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

    questions and how-tos

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     কিংবা
    0.58
     или
    0.54
     หรือ
    0.51
     –
    0.49
    ?
    0.48
     অথবা
    0.47
     —
    0.46
     혹은
    0.46
     And
    0.46
    หรือ
    0.44
    POSITIVE LOGITS
     لان
    0.48
    प्पी
    0.46
     suka
    0.45
     součást
    0.44
    下午
    0.41
    𒊑
    0.41
     substituir
    0.40
     په
    0.40
    LuaPush
    0.40
    സിൽ
    0.40
    Activations Density 0.011%

    No Known Activations