© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 203070
    Prev
    Next
    INDEX
    Explanations

    publication founded

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

    expectations, ground, promises

    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
    като
    0.51
    ?
    0.50
    ступ
    0.46
    риста
    0.46
     осе
    0.45
    하다
    0.45
    трима
    0.43
    인의
    0.43
    사에
    0.43
    거
    0.42
    POSITIVE LOGITS
     json
    0.54
     `$
    0.53
     `./
    0.51
     গিয়াছেন
    0.49
     `/
    0.48
     日
    0.47
     dp
    0.47
     `{
    0.47
    தமிழ்
    0.46
     hp
    0.46
    Activations Density 0.002%

    No Known Activations