© 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. 84855
    Prev
    Next
    INDEX
    Explanations

    listing items

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

    relationship deception and abuse

    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
     جات
    0.53
    非常的
    0.51
     इसलिये
    0.45
     फॉलोइंग
    0.43
     صاحب
    0.43
     ش
    0.43
     صندوق
    0.42
    非常有
    0.41
     choosing
    0.41
     دانشج
    0.40
    POSITIVE LOGITS
     accurately
    0.49
    ARKS
    0.47
    Sheep
    0.47
     recetas
    0.47
    Region
    0.45
    Representation
    0.45
    ತ್ತ
    0.44
    )&&
    0.44
     जलाश
    0.43
    ך
    0.43
    Activations Density 0.001%

    No Known Activations