© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4570
    Prev
    Next
    INDEX
    Explanations

    sequence continuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_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
    7
    1.46
    ₁,
    1.29
    6
    1.28
     dermal
    1.21
    8
    1.15
     Sora
    1.14
    ৭০
    1.13
    ۷
    1.12
    gebäude
    1.11
     modalities
    1.10
    POSITIVE LOGITS
     wherever
    1.56
     Probably
    1.44
     was
    1.41
     ไง
    1.40
     probably
    1.38
     Whatever
    1.36
     wasn
    1.35
     is
    1.34
    是很
    1.33
    是个
    1.31
    Activations Density 0.027%

    No Known Activations