© 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. 201670
    Prev
    Next
    INDEX
    Explanations

    noun followed by verb/preposition

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

    recorded events and observations

    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
     realises
    0.52
     తీసుకొ
    0.52
     réaliser
    0.52
    뎅
    0.52
    ratto
    0.51
     定义
    0.50
     Compagnie
    0.50
     océ
    0.50
     terão
    0.49
    𝙮
    0.49
    POSITIVE LOGITS
    Selected
    0.54
    ത്സ
    0.46
    <strong>
    0.45
    DOT
    0.44
    <em>
    0.43
    t
    0.43
    First
    0.43
    maturity
    0.43
    FM
    0.43
    mx
    0.42
    Activations Density 0.002%

    No Known Activations