© 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. 34161
    Prev
    Next
    INDEX
    Explanations

    specialized terms

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

    Upgrade and transpose

    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
    SHA
    0.64
     wyłącznie
    0.58
    のみ
    0.49
    ASSE
    0.48
    は
    0.48
    𝕌
    0.47
     basura
    0.47
    construct
    0.47
     organiza
    0.47
     کری
    0.46
    POSITIVE LOGITS
    nea
    0.43
     opposites
    0.42
     occasioned
    0.40
    irement
    0.40
    %$$
    0.39
    %
    0.39
     entanglement
    0.39
    aternion
    0.38
     mobilisation
    0.38
     iPads
    0.38
    Activations Density 0.000%

    No Known Activations