© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 102
    Prev
    Next
    INDEX
    Explanations

    mountains and geographical features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     Berliner
    0.83
    s
    0.80
     Staples
    0.79
    sgn
    0.78
     PUP
    0.75
     PUL
    0.74
     Stahl
    0.71
     York
    0.71
     OCE
    0.70
     Mulder
    0.70
    POSITIVE LOGITS
    call
    1.00
    峭
    0.84
     Mountain
    0.84
    Mountain
    0.84
    Mountains
    0.84
    calls
    0.82
     montagna
    0.82
    Throws
    0.82
     vallée
    0.82
    ле
    0.82
    Activations Density 0.128%

    No Known Activations