© 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. 79080
    Prev
    Next
    INDEX
    Explanations

    specific word sequences

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

    integrating automation partner packages dogs space Marketing

    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
     શ
    0.53
     Какой
    0.51
     صغير
    0.50
     గుర్
    0.50
    без
    0.50
     کوچک
    0.49
    PerRow
    0.49
     без
    0.48
    Recognition
    0.48
     صغيرة
    0.48
    POSITIVE LOGITS
    }
    0.71
     }
    0.49
    ]
    0.49
     spreadsheets
    0.45
    '}
    0.45
    meny
    0.45
    :}
    0.44
     dyst
    0.44
     preved
    0.44
     wasted
    0.43
    Activations Density 0.001%

    No Known Activations