© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2048
    Prev
    Next
    INDEX
    Explanations

    income, analysis, names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hips
    1.02
     grits
    0.86
    yship
    0.84
    cheduling
    0.84
    Pog
    0.79
    핍
    0.78
     digestibility
    0.77
     [/
    0.77
    obil
    0.77
    .[/
    0.77
    POSITIVE LOGITS
    SAND
    1.06
     Radon
    0.99
    Alf
    0.97
     lactate
    0.96
        
    0.95
     radon
    0.95
    3
    0.94
     Raut
    0.94
     Salman
    0.93
    ZERO
    0.93
    Activations Density 1.517%

    No Known Activations