© 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. 179351
    Prev
    Next
    INDEX
    Explanations

    evolved intoenter bothseries, "Irandom_1-10000entrepreneurs runningdivided intothought, when

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

    random number generation

    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
     lotion
    0.50
     HPV
    0.49
     lotions
    0.48
     wiggle
    0.47
     onscreen
    0.46
     uplink
    0.46
     ointment
    0.46
    櫒
    0.45
     Tendulkar
    0.45
     cheered
    0.44
    POSITIVE LOGITS
    src
    0.46
     terrenos
    0.44
     कारो
    0.44
    textbf
    0.43
    ái
    0.43
    lesson
    0.43
            
    0.42
    ʟ
    0.42
    jó
    0.42
    TAM
    0.42
    Activations Density 0.000%

    No Known Activations