© 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. 251374
    Prev
    Next
    INDEX
    Explanations

    proposed for

    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
     NAP
    0.50
     nazar
    0.46
     Fabi
    0.46
     पिन
    0.45
    ٽ
    0.45
     उमर
    0.44
     bet
    0.44
     больше
    0.44
     MALDI
    0.44
     graag
    0.43
    POSITIVE LOGITS
    )’
    0.55
    );
    0.51
    antuan
    0.51
    ih
    0.50
    Recurring
    0.50
    a
    0.48
    Pain
    0.48
    duction
    0.47
    Encrypt
    0.47
    ];
    0.47
    Activations Density 0.000%

    No Known Activations