© 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. 177128
    Prev
    Next
    INDEX
    Explanations

    pm on, showcase and, spike in, should not

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

    logic and concepts

    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
     =
    0.63
    ing
    0.60
    K
    0.52
      
    0.52
    =
    0.51
    the
    0.50
    P
    0.50
    Bs
    0.50
    Seconds
    0.49
        
    0.48
    POSITIVE LOGITS
     imigr
    0.51
    <unused2109>
    0.51
     ইন্টারনেট
    0.50
     stateMutability
    0.50
     reacciones
    0.50
     impenetr
    0.49
     Eugène
    0.49
    <unused2125>
    0.48
     Ärzte
    0.48
     muszą
    0.48
    Activations Density 0.000%

    No Known Activations