© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7541
    Prev
    Next
    INDEX
    Explanations

    cities and technical terms

    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
     இவர்
    0.91
     স্থানে
    0.88
    )(
    0.85
     オー
    0.85
    '));
    0.84
    ッフ
    0.84
     वर्मा
    0.82
    }}(
    0.82
    }({\
    0.82
    utenção
    0.81
    POSITIVE LOGITS
     altogether
    1.16
     inextricably
    1.14
     politics
    1.13
     itself
    1.11
     proper
    1.09
     Politics
    1.08
     anyway
    1.08
     anyhow
    1.06
     institutions
    1.04
    society
    1.03
    Activations Density 0.168%

    No Known Activations