© 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. 9892
    Prev
    Next
    INDEX
    Explanations

    silicates and oxides

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

    hydroxide and oxide compounds

    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
    }>
    0.39
     confl
    0.37
     cancer
    0.37
     disturbing
    0.37
     zinc
    0.36
     halluc
    0.36
     ver
    0.36
     recur
    0.36
     isoform
    0.36
     */
    0.35
    POSITIVE LOGITS
    Ꮘ
    0.40
    unky
    0.38
    باح
    0.38
    荡
    0.38
    
    0.38
    كا
    0.37
    华
    0.37
    초
    0.36
    乾隆
    0.36
    윌
    0.36
    Activations Density 0.002%

    No Known Activations