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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 253
    Prev
    Next
    INDEX
    Explanations

    mental health helplines

    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_22_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
     Math
    0.94
    าร์
    0.90
    asking
    0.84
    Math
    0.83
     Sander
    0.82
    ō
    0.81
    と思いますが
    0.79
    ሆነ
    0.79
     Schrödinger
    0.79
     Jason
    0.79
    POSITIVE LOGITS
    }~
    0.70
     προσ
    0.67
     [.
    0.67
    에
    0.66
     νό
    0.65
     velvety
    0.65
    ]?.
    0.65
    劾
    0.64
     πληροφο
    0.64
     ờ
    0.63
    Activations Density 0.002%

    No Known Activations