© 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. 116986
    Prev
    Next
    INDEX
    Explanations

    selection of images

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

    AI ML automating tasks

    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
    ClFN
    0.52
    但他
    0.51
    लेकिन
    0.48
    และการ
    0.48
     drzew
    0.47
    otor
    0.46
     但
    0.46
     त्यानंतर
    0.46
    और
    0.45
     ভবিষ্য
    0.45
    POSITIVE LOGITS
     démarche
    0.40
    كلمنا
    0.39
     $\{\
    0.38
    奋斗
    0.38
     togetherness
    0.38
     objectives
    0.37
     przedmiot
    0.37
    വിടെ
    0.37
     oure
    0.37
     $+\
    0.37
    Activations Density 0.000%

    No Known Activations