© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 132164
    Prev
    Next
    INDEX
    Explanations

    costs of services and features

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

    language and finance

    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
    ijnlijk
    0.49
    粎
    0.48
    akta
    0.47
     গুগল
    0.47
     পবিত্র
    0.47
    holo
    0.46
     すご
    0.45
     গুলির
    0.45
     বৃদ্ধ
    0.45
    portion
    0.44
    POSITIVE LOGITS
     refuses
    0.55
     muros
    0.50
    ])
    0.49
    어
    0.47
    َع
    0.46
    َد
    0.46
     comunidades
    0.46
     refuse
    0.46
     ciudadanía
    0.45
     intimid
    0.45
    Activations Density 0.000%

    No Known Activations