© 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. 160530
    Prev
    Next
    INDEX
    Explanations

    email following the

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

    A quiet

    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
    ya
    0.46
    </code>
    0.45
     britannique
    0.44
     تهران
    0.43
    li
    0.42
     bul
    0.42
    r
    0.42
     android
    0.42
    </a>
    0.42
    </strong>
    0.41
    POSITIVE LOGITS
     எழுத்த
    0.54
     Erschein
    0.52
    Substring
    0.51
    ೯
    0.50
     CONCLUS
    0.49
    Notas
    0.49
    を務
    0.48
     புகைப்பட
    0.48
    有利于
    0.47
     ਵਿੱਚ
    0.46
    Activations Density 0.001%

    No Known Activations