© 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. 183827
    Prev
    Next
    INDEX
    Explanations

    protect home and business

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

    of, if

    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
    склю
    0.49
     jiné
    0.47
    Utt
    0.47
     العن
    0.47
     ekki
    0.47
     utas
    0.46
    繭
    0.46
     ITable
    0.46
    紆
    0.46
     ceded
    0.45
    POSITIVE LOGITS
    BuildConfig
    0.46
     मॉड
    0.45
     బంగారం
    0.44
    }}/
    0.44
     एंड
    0.44
     ฉาก
    0.44
     Detect
    0.43
     काळात
    0.43
     गावा
    0.42
     टाइम्स
    0.42
    Activations Density 0.001%

    No Known Activations