© 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
    5. 12-GEMMASCOPE-2-RES-16K
    7. 41
    Prev
    Next
    INDEX
    Explanations

    job interview, website analysis, readings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_12_width_16k_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
    ="
    0.78
    ’
    0.76
     rumor
    0.75
     rumored
    0.72
    ，
    0.71
     denominator
    0.68
     rumour
    0.68
    ،
    0.67
    fashioned
    0.67
     entrenched
    0.66
    POSITIVE LOGITS
    ER
    0.93
     Alguns
    0.82
    ке
    0.73
    ное
    0.73
    AN
    0.72
    ECT
    0.71
    आर
    0.70
    ви
    0.69
    Algun
    0.69
    นี
    0.69
    Activations Density 6.960%

    No Known Activations