© 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. 56124
    Prev
    Next
    INDEX
    Explanations

    getty Princess

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

    actions ending in ing

    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
     barrio
    0.47
     portal
    0.47
    プレ
    0.46
     kate
    0.46
    術
    0.46
    認識
    0.46
     gre
    0.44
     courting
    0.44
     sulf
    0.44
     bluff
    0.44
    POSITIVE LOGITS
    gorod
    0.45
     Petersen
    0.44
     źród
    0.44
     واست
    0.44
    }.
    0.43
     Sidhu
    0.43
    Pitt
    0.43
    Pearson
    0.43
    Serializable
    0.42
     করেনি
    0.42
    Activations Density 0.000%

    No Known Activations