© 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. 195943
    Prev
    Next
    INDEX
    Explanations

    short-term consulting services

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

    following common articles

    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
    BUGFS
    0.48
    地铁
    0.47
     线
    0.46
     dialogo
    0.46
     региона
    0.45
    商城
    0.44
     선
    0.44
    ⏫
    0.43
    monton
    0.43
     지역
    0.43
    POSITIVE LOGITS
    certificates
    0.57
    سين
    0.46
    Ass
    0.46
    perger
    0.46
    سك
    0.45
    كس
    0.44
    كون
    0.44
    kami
    0.44
    Mask
    0.44
    كو
    0.43
    Activations Density 0.000%

    No Known Activations