© 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. 111829
    Prev
    Next
    INDEX
    Explanations

    latest news and developments

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

    protection and prevention

    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
    |।
    0.46
    ።
    0.46
    ]$.
    0.45
     വില
    0.45
     बीएड
    0.44
    একদিন
    0.43
    ָ
    0.43
    ។
    0.43
     प्लेयर्स
    0.42
    מוש
    0.42
    POSITIVE LOGITS
     protection
    0.45
     protecting
    0.44
     protects
    0.43
    過程
    0.43
    द्रता
    0.41
     защита
    0.41
     doğr
    0.40
     designing
    0.40
    ronomie
    0.40
     preventing
    0.39
    Activations Density 0.001%

    No Known Activations