© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 13349
    Prev
    Next
    INDEX
    Explanations

    mentioning specific examples

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_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
    ด้วย
    1.23
    కుంట
    1.17
    ла
    1.15
    many
    1.14
    แรง
    1.14
     عندها
    1.11
    ू
    1.08
    াই
    1.07
    కున్న
    1.07
    دد
    1.06
    POSITIVE LOGITS
     apocalyptic
    1.99
     policymakers
    1.93
     millennials
    1.93
     charismatic
    1.91
     eclectic
    1.91
     economist
    1.85
     monumental
    1.81
     nonprofit
    1.81
     elite
    1.81
     transformative
    1.78
    Activations Density 0.077%

    No Known Activations