© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3853
    Prev
    Next
    INDEX
    Explanations

    code or specific 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_7_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
     itself
    1.42
     north
    1.30
     raided
    1.28
     West
    1.25
     east
    1.25
     North
    1.24
    .__
    1.24
    <b>
    1.23
     northern
    1.22
    es
    1.21
    POSITIVE LOGITS
    ፆ
    1.95
     edades
    1.82
     mecanismos
    1.82
     modalités
    1.80
     pozitiv
    1.80
    punctuation
    1.80
     davranış
    1.79
    的数量
    1.78
     pozit
    1.77
     mecanismo
    1.76
    Activations Density 0.120%

    No Known Activations