© 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. 203634
    Prev
    Next
    INDEX
    Explanations

    ambitious art and engagement

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

    Gemma, understanding, originally

    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
    નો
    0.50
    ون
    0.49
     inversión
    0.47
    টি
    0.47
     وق
    0.47
     Pillar
    0.46
    كيد
    0.46
    ক
    0.45
    ০০০
    0.45
    IFUL
    0.45
    POSITIVE LOGITS
     ವಿಷಯ
    0.44
     desirable
    0.44
     thirteenth
    0.44
    ermann
    0.43
    facilit
    0.43
     lelaki
    0.42
    theit
    0.41
     ier
    0.41
     terse
    0.41
     awe
    0.40
    Activations Density 0.000%

    No Known Activations