© 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. 97132
    Prev
    Next
    INDEX
    Explanations

    company shares, house, elected

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

    get back to you

    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
    processors
    0.48
    jom
    0.45
     प्रोसेसर
    0.44
    utm
    0.44
    amps
    0.44
     आल
    0.43
    :~
    0.43
     चॉकलेट
    0.43
    ">(
    0.42
    ettings
    0.42
    POSITIVE LOGITS
    ं
    0.51
    তাকে
    0.46
    তে
    0.44
    能
    0.41
     relazioni
    0.40
     Consultation
    0.40
    가능
    0.40
     tzw
    0.40
     consultation
    0.39
    QUAL
    0.39
    Activations Density 0.000%

    No Known Activations