© 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. 77490
    Prev
    Next
    INDEX
    Explanations

    points behind

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

    relative position and proximity

    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
     красивые
    0.46
     بسیار
    0.46
    jeux
    0.44
     excellente
    0.43
    高温
    0.42
    饭
    0.42
     assez
    0.41
     Compatible
    0.41
     unprecedented
    0.41
     bravo
    0.41
    POSITIVE LOGITS
    ösen
    0.48
     unteren
    0.46
     nearest
    0.44
    closest
    0.44
     closest
    0.43
    nearest
    0.43
     താഴ
    0.42
     Krug
    0.41
    姩
    0.41
    そも
    0.40
    Activations Density 0.039%

    No Known Activations