© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31222
    Prev
    Next
    INDEX
    Explanations

    Multi-word phrases or specialized terms

    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_all/layer_41_width_262k_l0_big
    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
     ಒಳ್ಳೆಯ
    0.50
    zechoslovakia
    0.49
    noopener
    0.48
     communism
    0.46
    㚣
    0.44
    喝酒
    0.44
     offshoring
    0.44
    ötzlich
    0.44
    嫐
    0.44
     വൈദ്യുതി
    0.43
    POSITIVE LOGITS
     Multi
    0.49
     Mini
    0.47
     Enhanced
    0.47
     landscapes
    0.45
     Virtual
    0.44
     Advanced
    0.44
    Mini
    0.42
     multi
    0.42
     Resources
    0.42
     Assisted
    0.41
    Activations Density 0.004%

    No Known Activations