© 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. 75096
    Prev
    Next
    INDEX
    Explanations

    longitudinale and long

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

    AI scams and romantic deception

    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
    на
    0.57
    افظ
    0.55
    до
    0.50
    ј
    0.47
    довать
    0.45
    耀
    0.45
    говор
    0.45
    ю
    0.44
    дох
    0.44
    мато
    0.43
    POSITIVE LOGITS
     bilater
    0.46
     놀
    0.46
    versi
    0.46
    bil
    0.45
     سما
    0.45
     longitudinale
    0.45
     reintegr
    0.45
     انہیں
    0.44
     सब
    0.44
     basses
    0.44
    Activations Density 0.001%

    No Known Activations