© 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. 110626
    Prev
    Next
    INDEX
    Explanations

    domain name registration

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

    gods, conceive, despite differences

    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
     〈
    0.47
    .}}
    0.45
    dwell
    0.43
     င
    0.43
     })}
    0.42
     パ
    0.42
    typeface
    0.42
    ไม่
    0.41
    istors
    0.41
    occasion
    0.41
    POSITIVE LOGITS
    两条
    0.50
     batalha
    0.48
     pouquinho
    0.48
     এসএসসি
    0.47
    뜻
    0.46
    ابی
    0.45
     activación
    0.44
    ضرب
    0.44
     induc
    0.44
    욬
    0.44
    Activations Density 0.001%

    No Known Activations