© 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. 73461
    Prev
    Next
    INDEX
    Explanations

    knowing and risk

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

    vintage items and lucrative ventures

    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
    ന്മാ
    0.48
    스포츠
    0.47
    Mans
    0.47
    지
    0.45
     ፣
    0.43
     Mansfield
    0.42
    mä
    0.41
    骑士
    0.41
    骞
    0.41
    ജ
    0.41
    POSITIVE LOGITS
     करोड़
    0.49
     relembrar
    0.46
     अनुशंसा
    0.45
     млн
    0.44
     remarquer
    0.44
     निव
    0.44
     কয়েক
    0.44
     keter
    0.44
     بودند
    0.44
     esperar
    0.43
    Activations Density 0.000%

    No Known Activations