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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 13939
    Prev
    Next
    INDEX
    Explanations

    priorities within, misinformation during

    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_13_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
    ธ
    0.95
    tz
    0.92
    თ
    0.91
    渐
    0.88
     জের
    0.87
    Belt
    0.85
     เบ
    0.85
     Bert
    0.81
     ve
    0.81
    Bert
    0.80
    POSITIVE LOGITS
     again
    0.98
     Again
    0.94
    }']
    0.89
    こちらも
    0.88
     ']
    0.87
    }"]
    0.87
     initComponents
    0.86
     AGAIN
    0.84
     Secundaria
    0.84
     उसी
    0.83
    Activations Density 0.794%

    No Known Activations