© 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. 190059
    Prev
    Next
    INDEX
    Explanations

    saving our country

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

    concerns, or stakeholders

    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
     wildflowers
    0.55
     receptors
    0.52
     robes
    0.50
     lateribus
    0.49
     warmed
    0.49
    🎹
    0.47
     transparencia
    0.47
    🐃
    0.46
     phosphorylated
    0.45
    および
    0.45
    POSITIVE LOGITS
    HA
    0.49
     ഇവിടെ
    0.49
    віта
    0.48
    దా
    0.47
    PA
    0.47
    OK
    0.47
    arlal
    0.47
     Residency
    0.46
    MAS
    0.46
    tinger
    0.45
    Activations Density 0.001%

    No Known Activations