© 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. 161287
    Prev
    Next
    INDEX
    Explanations

    very beautiful old child information data

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

    risk tolerance and investing

    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
     visualise
    0.52
    不止
    0.51
    ™,
    0.48
     pressione
    0.47
     cento
    0.47
     conclusione
    0.46
     destra
    0.46
     embar
    0.46
     Councilor
    0.46
     espl
    0.46
    POSITIVE LOGITS
     урав
    0.54
    ార్
    0.48
    гура
    0.48
    مركز
    0.47
    稅
    0.45
    方程
    0.45
    ర్య
    0.44
    acr
    0.44
    న్య
    0.44
    넵
    0.43
    Activations Density 0.000%

    No Known Activations