© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 23324
    Prev
    Next
    INDEX
    Explanations

    When followed by article or pronoun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     δημ
    0.46
     मायने
    0.45
     думать
    0.44
     ਗਿਆ
    0.44
     появились
    0.42
    웠
    0.42
     эффек
    0.41
    ନ
    0.40
     podía
    0.40
    ologico
    0.40
    POSITIVE LOGITS
     someone
    0.66
    someone
    0.55
    有人
    0.49
     seseorang
    0.48
     receives
    0.48
     کوئی
    0.46
     detecting
    0.46
     encountering
    0.46
     recebe
    0.44
     receiving
    0.44
    Activations Density 0.009%

    No Known Activations