© 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. 203251
    Prev
    Next
    INDEX
    Explanations

    specific entities or common words followed by specific punctuation or verbs

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

    qualifier or introductory word

    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
    ’
    0.57
    ile
    0.54
     seperti
    0.53
    :
    0.51
     national
    0.48
    .
    0.48
    am
    0.46
     is
    0.45
    ul
    0.45
    ullah
    0.45
    POSITIVE LOGITS
    目的地
    0.49
     पूजन
    0.47
    臀
    0.46
    Mâc
    0.45
    INUS
    0.45
    StillWater
    0.43
     φι
    0.42
     言っ
    0.42
    鷸
    0.42
     الكل
    0.41
    Activations Density 0.000%

    No Known Activations