© 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. 194041
    Prev
    Next
    INDEX
    Explanations

    real threat, jar tickets, settle for, succeed in

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

    psychological immersion or distance

    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
    Hp
    0.48
    PlayerSelector
    0.46
    మార్
    0.45
    詼
    0.45
     ప్రతి
    0.45
    []');
    0.45
     الحاس
    0.44
     हफ्ते
    0.44
     насы
    0.44
    チュ
    0.43
    POSITIVE LOGITS
     endophytic
    0.47
     abroad
    0.46
    .—
    0.46
     whiff
    0.45
    ov
    0.45
     coronal
    0.45
     किरण
    0.45
     airborne
    0.44
    ě
    0.43
     worker
    0.43
    Activations Density 0.000%

    No Known Activations