© 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. 4112
    Prev
    Next
    INDEX
    Explanations

    text conversion and automation

    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
    relativePath
    1.37
     marshm
    1.33
     Española
    1.31
     Resting
    1.27
     Tajikistan
    1.26
    azionali
    1.26
    agram
    1.25
    姿
    1.25
    arettes
    1.24
    ">–
    1.23
    POSITIVE LOGITS
     demethyl
    1.23
     dye
    1.15
     фабри
    1.14
     جه
    1.14
     королев
    1.11
     pulp
    1.09
    kop
    1.07
     flesh
    1.07
     Mainz
    1.06
     моло
    1.05
    Activations Density 0.013%

    No Known Activations