© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    recipes, expert roles, discourse markers

    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
    1.38
    6
    1.31
    Damage
    1.27
     RBD
    1.24
    4
    1.23
    Failure
    1.23
     Damage
    1.20
     Catedral
    1.16
    5
    1.15
    tres
    1.14
    POSITIVE LOGITS
     iu
    1.19
    pan
    1.17
     discussed
    1.08
     Aust
    1.07
    ported
    1.06
     sud
    1.05
    ivers
    1.04
     trate
    1.04
    อิน
    1.04
     VL
    1.03
    Activations Density 0.010%

    No Known Activations