© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2901
    Prev
    Next
    INDEX
    Explanations

    provide list, business ideas, benefit from

    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
     Québec
    1.18
     Sprague
    1.15
     Calgary
    1.15
     Sask
    1.15
    3
    1.11
     Quebec
    1.11
    6
    1.05
    7
    1.04
    req
    1.02
    8
    1.00
    POSITIVE LOGITS
     Lov
    1.11
     Mare
    1.11
     Vicar
    1.11
     Hepat
    1.10
     Putt
    1.10
     速
    1.09
     EET
    1.08
     Puppet
    1.06
     Fam
    1.06
     Alias
    1.05
    Activations Density 0.063%

    No Known Activations