© 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. 188370
    Prev
    Next
    INDEX
    Explanations

    Palm Beach & Hibbing

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

    balanced argument and desire

    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
     কুল
    0.52
    কুল
    0.47
     छापे
    0.45
     نص
    0.45
    ل
    0.44
    சிய
    0.44
    دين
    0.43
     Kraft
    0.43
    poste
    0.43
     cuál
    0.42
    POSITIVE LOGITS
    部の
    0.59
    Elem
    0.52
    子の
    0.50
    ент
    0.48
    期の
    0.48
    ELEMENT
    0.47
    Hyp
    0.47
    ]]))
    0.46
    "]
    0.46
    子が
    0.45
    Activations Density 0.001%

    No Known Activations