© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 38484
    Prev
    Next
    INDEX
    Explanations

    down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    j
    0.62
    0.58
    dd
    0.55
    dat
    0.55
    v
    0.55
    }`)
    0.55
    dob
    0.55
    دي
    0.54
     ifelse
    0.54
    }:\
    0.54
    POSITIVE LOGITS
     down
    1.14
    ลง
    0.88
     xuống
    0.86
     Down
    0.86
    edown
    0.86
    下来
    0.83
    down
    0.82
     डाउन
    0.82
     내려
    0.81
     downs
    0.79
    Activations Density 0.060%

    No Known Activations