© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14732
    Prev
    Next
    INDEX
    Explanations

    as being / egress in / force helps / hold back / exposure can / ninguna preferencia

    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_13_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
    le
    0.76
     bzw
    0.67
    or
    0.65
     and
    0.64
    id
    0.63
    <0xE7>
    0.63
    legal
    0.63
    config
    0.62
    lo
    0.62
    ge
    0.61
    POSITIVE LOGITS
    𒐈
    1.28
     சைவமணி
    1.25
    
    1.25
    𒐁
    1.23
    opencamer
    1.23
    𒀔
    1.23
    𒐏
    1.23
    𒆯
    1.22
    ⦖
    1.22
    𒐻
    1.22
    Activations Density 0.000%

    No Known Activations