© 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-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5843
    Prev
    Next
    INDEX
    Explanations

    risk and threats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
    <0x99>
    0.79
     Burlington
    0.71
     Butterworth
    0.66
    Normalization
    0.66
     Sumner
    0.66
     fabricating
    0.65
    Marcel
    0.65
     záz
    0.65
    elton
    0.65
    ঊ
    0.65
    POSITIVE LOGITS
     risks
    2.24
     risk
    2.19
     Risk
    2.15
    Risk
    2.14
     Risks
    2.13
    risk
    2.05
     threat
    1.90
     riesgo
    1.88
     riesgos
    1.87
     risco
    1.85
    Activations Density 0.539%

    No Known Activations