© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 2050
    Prev
    Next
    INDEX
    Explanations

    predictable behavior

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     націона
    0.58
     National
    0.56
     naut
    0.54
    orn
    0.53
     Specimens
    0.52
     N
    0.51
     News
    0.51
     Ministry
    0.50
    _
    0.49
     aparel
    0.49
    POSITIVE LOGITS
     predictability
    1.41
     deterministic
    1.28
     rigidity
    1.24
     monotonicity
    1.17
     transparency
    1.16
     guarantees
    1.16
     predictable
    1.13
     symmetric
    1.12
     constraint
    1.08
     rigid
    1.08
    Activations Density 2.412%

    No Known Activations