© 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. 3929
    Prev
    Next
    INDEX
    Explanations

    processes and options

    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
    2
    1.12
    3
    1.12
    Background
    1.07
    End
    1.05
    7
    1.05
    end
    1.04
    1.03
     end
    1.01
    4
    1.01
    1
    1.00
    POSITIVE LOGITS
     ASF
    1.30
    Ei
    1.21
    ҽ
    1.20
     amma
    1.17
     sherry
    1.15
     showcase
    1.14
     SNA
    1.14
    VAS
    1.11
     Lice
    1.09
     ALLEN
    1.09
    Activations Density 0.000%

    No Known Activations