© 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. 97836
    Prev
    Next
    INDEX
    Explanations

    charging or resistant to attacks

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

    avatars and fantastic descriptions

    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
     بواسط
    0.47
    μένος
    0.46
    IMIENTO
    0.45
    émique
    0.44
    াপ্র
    0.44
    濕
    0.44
    
    0.43
    Sistema
    0.43
    譽
    0.43
     поддер
    0.42
    POSITIVE LOGITS
     r
    0.49
     Subtle
    0.47
     l
    0.46
     Speak
    0.46
     bő
    0.45
     Speaking
    0.45
     entfernen
    0.44
     Precambrian
    0.44
    شي
    0.44
    改成
    0.44
    Activations Density 0.001%

    No Known Activations