© 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. 226421
    Prev
    Next
    INDEX
    Explanations

    amplified designs

    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
    会社の
    0.46
    risque
    0.46
    HTTP
    0.46
    醬
    0.46
     võimal
    0.45
    🫧
    0.45
    ě
    0.45
    🤘
    0.44
    応援
    0.43
    POSITIVE LOGITS
     beiden
    0.50
    }=\
    0.49
     Consejo
    0.47
     trifling
    0.46
     COUNCIL
    0.44
    }=
    0.44
     takim
    0.43
    }=(-
    0.42
     двумя
    0.41
     Council
    0.40
    Activations Density 0.000%

    No Known Activations