© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 4460
    Prev
    Next
    INDEX
    Explanations

    up-to-date information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    lication
    0.94
    ໃຊ
    0.89
    രക്ഷ
    0.85
     Seç
    0.84
     மாநிலத்தில்
    0.83
    ຢ
    0.82
    iędzy
    0.82
    Გ
    0.82
    یث
    0.82
    unication
    0.81
    POSITIVE LOGITS
     >>
    0.75
     correct
    0.65
    ima
    0.63
     top
    0.61
     →
    0.60
    積み
    0.58
     missing
    0.57
    ten
    0.57
     >
    0.54
     acres
    0.53
    Activations Density 0.018%

    No Known Activations