© 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. 76279
    Prev
    Next
    INDEX
    Explanations

    what your

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

    Spanish phrases and meaning

    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
    וד
    0.54
    ტ
    0.49
    鑽
    0.49
    ટ
    0.47
     काम
    0.47
    ٹ
    0.47
    营销
    0.46
    ଧ
    0.46
    ешь
    0.46
    鎴
    0.45
    POSITIVE LOGITS
     vorhanden
    0.49
     Florida
    0.46
     interferes
    0.44
     immortality
    0.42
     understand
    0.42
     eikä
    0.42
     detachable
    0.42
     Titanic
    0.41
     embryos
    0.41
     interfere
    0.41
    Activations Density 0.004%

    No Known Activations