© 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. 40577
    Prev
    Next
    INDEX
    Explanations

    God, joy, husbands

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

    semen containing

    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
    1
    0.66
    4
    0.58
    2
    0.55
    8
    0.48
    5
    0.46
    Bright
    0.45
    Bradley
    0.44
    Aqu
    0.44
    De
    0.44
    lining
    0.44
    POSITIVE LOGITS
     క్ష
    0.57
    überkü
    0.54
     죄
    0.51
    NeedConnect
    0.51
     उर्व
    0.50
     Gespräch
    0.49
     Mitgl
    0.49
     சின்னமாக
    0.49
     giver
    0.48
     candidat
    0.48
    Activations Density 0.000%

    No Known Activations