© 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. 193426
    Prev
    Next
    INDEX
    Explanations

    oral or written notice

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

    working conditions, careful actions, combination options

    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
    尼
    0.51
     কৌশ
    0.50
    am
    0.49
     नीला
    0.47
    นี
    0.47
    恬
    0.46
    ala
    0.46
     blå
    0.46
    arna
    0.46
    לא
    0.46
    POSITIVE LOGITS
     deceleration
    0.48
    Specificity
    0.46
     narrative
    0.44
     launchers
    0.44
     comprehend
    0.43
     solvency
    0.43
     /=
    0.41
    тента
    0.41
     begleitet
    0.41
     rhyme
    0.41
    Activations Density 0.001%

    No Known Activations