© 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. 218655
    Prev
    Next
    INDEX
    Explanations

    s, sustainable, exhibits, acquired, borrows, overlay, acquired

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

    cognitive dissonance

    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
     её
    0.51
    ñ
    0.48
    ፦
    0.48
     لوبوي
    0.48
    that
    0.48
     ejército
    0.46
    erea
    0.46
     hôm
    0.45
    drá
    0.45
     vil
    0.44
    POSITIVE LOGITS
    ESSION
    0.54
    OMI
    0.45
     Szen
    0.44
    Լ
    0.44
    ᕋ
    0.44
    ாரு
    0.44
     वैलेंट
    0.44
    మ్మ
    0.44
    滏
    0.44
     przek
    0.43
    Activations Density 0.000%

    No Known Activations