© 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. 90970
    Prev
    Next
    INDEX
    Explanations

    new/abyss/ship/deserve/Mr/Glass/this/was followed by specific words

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

    dark colors, death, file, /*, Medina, uncertain

    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
    Negative Logits
    },
    0.52
    }(
    0.48
    했다
    0.48
    }$.
    0.46
    吃
    0.46
     publicada
    0.45
    }$,
    0.44
     تعرض
    0.44
    }
    0.44
    }+
    0.43
    POSITIVE LOGITS
    lemma
    0.51
    لک
    0.49
    SCH
    0.48
    ောင်
    0.48
     bhikkhu
    0.47
     Quellen
    0.45
     SCH
    0.45
     subdirectory
    0.45
    ه‌ی
    0.45
    RootManager
    0.44
    Activations Density 0.001%

    No Known Activations