© 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. 36925
    Prev
    Next
    INDEX
    Explanations

    giving or giving something

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

    provides benefit or advantage

    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
     perj
    0.47
     bribes
    0.47
    ћа
    0.45
     gentamicin
    0.45
    NewUrl
    0.43
     regalos
    0.43
     flaws
    0.42
    汢
    0.42
     تحد
    0.41
     nexus
    0.41
    POSITIVE LOGITS
    WE
    0.43
     mengalami
    0.43
    ៉
    0.40
    otted
    0.39
    MRP
    0.39
     breathing
    0.38
    ทะ
    0.38
    PROCESSING
    0.38
    processing
    0.38
     breathed
    0.38
    Activations Density 0.042%

    No Known Activations