© 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. 66011
    Prev
    Next
    INDEX
    Explanations

    actions and consequences

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

    money, management, satisfaction

    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
    idE
    0.50
    ים
    0.50
    だけど
    0.50
    Σ
    0.48
    ㊗
    0.48
    מה
    0.47
    ע
    0.46
     изделий
    0.46
    ג
    0.46
    Produto
    0.46
    POSITIVE LOGITS
    smanship
    0.47
    ovaž
    0.47
     illegally
    0.45
    )^{\
    0.44
     succumbed
    0.44
     সাহস
    0.44
     regrett
    0.43
     bravely
    0.42
     fined
    0.42
     haría
    0.42
    Activations Density 0.000%

    No Known Activations