© 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. 204276
    Prev
    Next
    INDEX
    Explanations

    past tense verbs and possessives

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

    keyword research

    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
    ценка
    0.51
    Loops
    0.50
     dirt
    0.46
    Yaw
    0.46
    olphin
    0.46
    시킨
    0.45
    왑
    0.44
    ustainable
    0.43
    dropPanel
    0.43
    시키는
    0.43
    POSITIVE LOGITS
     seit
    0.49
    燦
    0.46
    ]
    0.44
     Rm
    0.43
     টানা
    0.43
     ១
    0.42
     বাড়
    0.41
    以來
    0.40
     Jefe
    0.39
    我們要
    0.39
    Activations Density 0.000%

    No Known Activations