© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 30306
    Prev
    Next
    INDEX
    Explanations

    feelings and scores

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    NgramModel
    0.46
    Execute
    0.45
    Fiscal
    0.44
    WaitFor
    0.43
    Measure
    0.42
    Patrick
    0.42
    赸
    0.42
     enterprise
    0.41
     gode
    0.41
    ृह
    0.41
    POSITIVE LOGITS
     is
    0.46
    
    0.45
    cdot
    0.42
    ént
    0.40
    பர்
    0.40
    傷害
    0.39
     undeniably
    0.39
    áin
    0.39
     grounds
    0.39
     admits
    0.39
    Activations Density 0.007%

    No Known Activations