© 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. 76645
    Prev
    Next
    INDEX
    Explanations

    mesh pockets and bottle holders

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

    for you

    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
     નિ
    0.49
    ಿಸಬಹುದು
    0.48
     높은
    0.45
     можем
    0.41
    丨
    0.41
     inability
    0.40
     죄
    0.40
    ᵕ
    0.40
    显然
    0.39
    보
    0.39
    POSITIVE LOGITS
    اك
    0.48
    كال
    0.47
    طي
    0.45
     facteurs
    0.45
    仲間
    0.44
    لاك
    0.44
     tzw
    0.44
    ίζουν
    0.43
    AKA
    0.43
    র্জ
    0.42
    Activations Density 0.006%

    No Known Activations