© 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. 11422
    Prev
    Next
    INDEX
    Explanations

    strong emotions

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

    visible emotional states

    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
    दक्षिण
    0.43
     currencies
    0.42
    ब्रिट
    0.41
    नीचर
    0.41
    EDIA
    0.40
     reputations
    0.40
     ওয়েস্ট
    0.40
    }_{-
    0.39
     निवेशक
    0.39
    經常
    0.39
    POSITIVE LOGITS
     tinge
    0.57
     flashes
    0.51
     Worte
    0.51
     느껴
    0.50
     smirk
    0.50
    微微
    0.46
     বাণী
    0.44
    的看着
    0.43
     unmistakable
    0.42
    佻
    0.42
    Activations Density 0.025%

    No Known Activations