© 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. 46634
    Prev
    Next
    INDEX
    Explanations

    deepest needs, really up, will always

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

    promise, hold, worth, industries, inch

    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
     fungi
    0.52
     fungus
    0.50
    ऊस
    0.46
     litre
    0.45
    さを
    0.45
     earthen
    0.45
    ̯
    0.44
     bonnes
    0.44
     matematika
    0.43
    文本
    0.43
    POSITIVE LOGITS
     المقص
    0.51
    gäng
    0.50
     도
    0.44
     المتح
    0.44
    ixed
    0.44
    gat
    0.42
    所で
    0.41
     ליי
    0.40
    員
    0.40
            
    0.40
    Activations Density 0.000%

    No Known Activations