© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 228873
    Prev
    Next
    INDEX
    Explanations

    conclusion and process

    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
     политика
    0.56
     участия
    0.53
     राजनीति
    0.51
     участие
    0.48
    讨厌
    0.48
    蝓
    0.47
     політи
    0.47
    ສາ
    0.47
     полити
    0.47
    參数
    0.46
    POSITIVE LOGITS
    6
    0.50
     is
    0.48
    <start_of_image>
    0.43
    8
    0.42
    },
    0.42
     C
    0.41
     Bud
    0.41
     wenig
    0.40
    ↵↵
    0.40
     Pre
    0.40
    Activations Density 0.004%

    No Known Activations