© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8134
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions followed by conditional phrases

    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_31_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
    a
    0.66
     is
    0.61
     the
    0.58
     was
    0.57
    2
    0.55
    an
    0.53
    hearted
    0.49
    inspired
    0.48
    :
    0.47
     springs
    0.47
    POSITIVE LOGITS
    Сан
    0.60
    銠
    0.58
    يد
    0.56
     électron
    0.56
    ιν
    0.55
    ين
    0.54
    Сейчас
    0.54
    ري
    0.53
    حي
    0.53
    Види
    0.53
    Activations Density 0.000%

    No Known Activations