© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 27535
    Prev
    Next
    INDEX
    Explanations

    training/combat duration computer app budget talk

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ī
    0.56
    ū
    0.51
    };
    0.50
    ="
    0.49
     Перейти
    0.47
     fi
    0.47
     большинства
    0.46
    ă
    0.45
     √
    0.44
    {\
    0.44
    POSITIVE LOGITS
    م
    0.77
    ر
    0.73
    ع
    0.69
    em
    0.69
    the
    0.66
    ق
    0.66
    म
    0.65
    am
    0.65
    ко
    0.64
    ли
    0.64
    Activations Density 0.097%

    No Known Activations